Careers
Join us
Our people are our greatest asset.
We pride ourselves on attracting the most talented individuals. Our interdisciplinary team combines expertise in biology, medicine, clinical pharmacology, applied mathematics, data science, artificial intelligence, and software development.
Why Nova
The Nova extras
Dynamic in a caring environment
You will work with strongly motivated people who will help you navigate a steep learning curve, in a supportive atmosphere.
Multidisciplinary background
We are a team of 50+ people with expertise in biology, applied mathematics, and computer science.
Multicultural team
We speak English, Italian, Arabic, Russian, German, Portuguese, Japanese, Spanish, and even a little French.
Friendly atmosphere
Work hard, play hard. We love spending downtime as a team: tarot during breaks, running at lunchtime, or cold drinks after work.
Join the team
Open positions
Business unit
Contract type
QSP Modeler
Nova In Silico is a pioneer in the emerging field of In Silico clinical trials based in Lyon (France). It specializes in numerical modeling and simulation of clinical trials for biotech and pharmaceutical companies, academic research centers and non-profit organizations. We help our clients unleash the potential of combining math, computer science and biology to reduce the risks associated with R D of new treatments. Through collaborative work, our team of biologists, medical doctors, clinicians, mathematicians and computer scientists develop multiscale mechanistic models in various fields such as oncology, cardiology, immune disorder, viral infections or metabolic diseases. The QSP modeler will play a crucial role in advancing our In Silico clinical trials, contributing directly to the development of safer and more effective treatments for the benefit of patients. We are looking for a passionate and skilled individual who is: A team player, a good listener, and an effective communicator Join a growing multidisciplinary team of enthusiastic innovators such as biologists, data scientists, applied math engineers and developers. Curious and proactive with a solid grounding in biology and/or mathematical modeling, particularly in systems biology,QSP modeling, PK/PD modeling, cell and molecular biology, and omics, to address real-life clinical issues. Eager to learn and use mathematical methods for the modeling of biological systems Simulate virtual diseases and treatments with ODE, PDE, Monte-Carlo Simulations. Willing to explore and exploit large datasets and virtual populations Apply machine learning, statistical analysis, and outliers detection. Autonomous and self-motivated with strong analytical and problem-solving skills Find innovative solutions to science and engineering problems. Responsive and capable of facing time-sensitive challenges. Project management with client-facing opportunities are awaiting you. RESPONSIBILITIES Actively contribute to the creation of In Silico disease and drug models : Conduct thorough literature reviews on the biological system to model Develop computational models (CM) of biological systems Calibrate models based on extracted data knowledge Integrate models with others to build larger more comprehensive models Run and analyze large simulation results to answer the client’s questions Communicate your results in scientific reports and presentations Impact the development of the company’s simulation platform Actively participate in weekly and monthly project meetings and reporting QUALIFICATIONS One of the following qualifications: MSc in Engineering, Applied Mathematics, Computational Biology, Systems Biology, or a closely related quantitative discipline Engineering degree (or equivalent) with a strong quantitative background PhD in Computational Biology, Systems Biology, Applied Mathematics or a related field Along with: Strong background in mathematical modelling and/or systems biology Knowledge or strong interest in biology, biochemistry, and/or pharmaceutical sciences Experience with at least one scientific programming language (language is not critical) Professional proficiency in English (written and spoken) As a bonus: Experience in mechanistic modeling (systems biology, QSP, PB-PKPD) Experience in modeling techniques (ODEs, PDEs, DDEs, Agent-based) Knowledge of clinical trials and drug development TECHNOLOGIES We are looking for someone who is eager to learn/work with the following technologies (or knows them): Unix environment Programming languages (Haskell, Python, R Agentic AI (Claude Code, Codex, MCP, skills) Markup languages (Markdown, LaTeX) Miscellaneous (Git, bash) MISC Type: full-time job, based in Lyon, France Contact: recruitment@novainsilico.ai Starting date: from Sept 2026 WELL-BEING AT WORK Nova offers a modern, pleasant and stimulating work environment, conducive to creativity and innovation We cultivate a strong team spirit based on mutual support, collaboration and sharing Our company culture promotes a healthy work-life balance for sustainable fulfillment The company allows flexibility in work organization including teleworking up to 2 days a week and offers various benefits We encourage socializing outside of work, both on and off site (theme evenings, outings, film club, etc.)
Machine Learning Intern — Stochastic Gradient Descent
Nova In Silico is a health tech company that develops an in silico clinical trial platform jinkō to simulate drug efficacy and optimize clinical development using virtual patients and disease modeling. As an innovative company, we offer a dynamic work environment distinct from larger, established organizations. Interns will gain significant responsibilities and benefit from a steep learning curve, supported by a highly motivated team. KEYWORDS Expectation Maximization, Gradient Descent, Non-Linear Mixed-Effects Model, Surrogate Model, PyTorch BACKGROUND — QUANTITATIVE SYSTEMS PHARMACOLOGY AND ITS CHALLENGES Quantitative Systems Pharmacology (QSP) is a critical discipline in modern drug development. It involves creating complex, mechanistic mathematical models that describe the dynamic interactions between a drug and a biological system. These models integrate pathophysiology and pharmacology to predict a drug's effect, safety, and efficacy across diverse patient populations. At Nova In Silico, our R D efforts are focused on building and applying these high-fidelity QSP models. A significant challenge arises when fitting these models to real-world clinical data. To account for variability between individuals, QSP models are often formulated as Non-Linear Mixed-Effects (NLME) models. Parameter estimation for NLME models, which is typically performed via Maximum Likelihood Estimation (MLE), is a difficult and computationally intensive task. Traditional estimation algorithms can take hours or even days to converge, creating a substantial bottleneck in the R D pipeline. PYTORCH-BASED SURROGATE MODELS To address this computational bottleneck, Nova In Silico has successfully developed surrogate models for some of our key QSP models. These surrogates, built using the PyTorch deep learning framework, are lightweight, fast-to-execute approximations of the full, complex QSP models. They are designed to capture the essential input-output behavior of the original model while dramatically reducing computation time. This speed-up has enabled us to more efficiently perform parameter estimation. Currently, we leverage our surrogate models within Expectation-Maximization (EM) type algorithms. EM is a powerful and standard method for finding maximum likelihood estimates in models with latent variables (such as the random effects in NLME models). This approach has proven effective for our existing model structures. FLEXIBLE ESTIMATION VIA STOCHASTIC GRADIENT DESCENT While effective, EM-type algorithms are often tailored to specific model structures and statistical assumptions. As our R D pipeline evolves, we aim to explore more diverse and complex surrogate model architectures and apply them to various types of clinical data. The mathematical framework of EM can be restrictive in these more general cases. Stochastic Gradient Descent (SGD) offers a compelling and flexible alternative, as these algorithms: Can be applied to a much broader family of models and data structures. Are often more computationally efficient, as they can process large datasets in small batches. Integrate natively with the PyTorch ecosystem, as gradient computation is the framework's core function. OBJECTIVE The intern will implement the stochastic approximation gradient algorithm, drawing from the principles in the reference articles, and apply it to our existing surrogate models. This will equip Nova In Silico with a novel, flexible, and powerful estimation tool, expanding our capabilities to fit next-generation QSP models to complex clinical data. YOU ARE A team player , a good listener, and an effective communicator Curious and proactive , ready to face real-life engineering challenges Autonomous and self-motivated with strong analytical and problem-solving skills Eager to learn mathematical modeling and simulations of biological systems Willing to explore latest advances in science and technology Responsive and capable of tackling time-sensitive issues with agility YOU WILL Review the scientific literature on relevant machine learning algorithms Prototype the stochastic gradient algorithm under Nova's specific constraints Evaluate benchmark cases against the alternative SAEM algorithm Integrate solutions into Nova's simulation platform METHODOLOGY AND TECHNICAL SKILLS We are looking for people who know some of the following or are eager to learn and work with them: Machine learning in Python, PyTorch Statistical modeling, NLME models A professional English level (written and oral) is required for this role. PRACTICAL INFORMATION Apply directly on our careers page Contact: recruitment@novainsilico.ai Salary: Competitive Start date: Flexible
Machine Learning Intern — ML-Based Surrogate Models
Nova In Silico is a health tech company that develops an in silico clinical trial platform jinkō to simulate drug efficacy and optimize clinical development using virtual patients and disease modeling. As an innovative company, we offer a dynamic work environment distinct from larger, established organizations. Interns will gain significant responsibilities and benefit from a steep learning curve, supported by a highly motivated team. KEYWORDS Surrogate Model, Gaussian Process, Neural Networks, Optimization, Classification, PyTorch BACKGROUND — QUANTITATIVE SYSTEMS PHARMACOLOGY AND ITS CHALLENGES Quantitative Systems Pharmacology (QSP) is a critical discipline in modern drug development. It involves creating complex, mechanistic mathematical models that describe the dynamic interactions between a drug and a biological system. These models integrate pathophysiology and pharmacology to predict a drug's effect, safety, and efficacy across diverse patient populations. At Nova In Silico, our R D efforts are focused on building and applying these high-fidelity QSP models. A significant challenge arises when fitting these models to real-world clinical data. To account for variability between individuals, QSP models are often formulated as Non-Linear Mixed-Effects (NLME) models. Parameter estimation for NLME models, which is typically performed via Maximum Likelihood Estimation (MLE), is a difficult and computationally intensive task. Traditional estimation algorithms can take hours or even days to converge, creating a substantial bottleneck in the R D pipeline. CURRENT SURROGATE MODELS AND LIMITATIONS To address this computational bottleneck, Nova In Silico has successfully developed surrogate models for some of our key QSP models. These surrogates are lightweight, fast-to-execute approximations of the full, complex QSP models, built using the PyTorch framework. Their purpose is to capture the essential input-output relationship of the original model while reducing computation time by orders of magnitude. This speed-up has been instrumental, enabling us to efficiently perform parameter estimation using standard algorithms like Expectation-Maximization (EM). Our current generation of surrogate models is primarily based on Gaussian Processes (GPs). GPs are a powerful non-parametric statistical method, well-regarded for their ability to interpolate in low-dimensional spaces and, crucially, to provide a principled measure of uncertainty for their predictions. However, GPs also present significant limitations. Their computational complexity scales poorly with the size of the training dataset, making them cumbersome for large-scale simulations. More importantly, they are inherently designed for continuous, smooth functions. This underlying assumption makes it challenging to model the complex realities of clinical data and QSP simulations, which are often neither simple nor smooth. FLEXIBLE ML-BASED SURROGATE MODELS Machine learning or deep learning models, which can be implemented seamlessly within our existing PyTorch ecosystem, provide a new level of flexibility that can directly address the shortcomings of GPs and achieve two key advantages: Handling heterogeneous inputs (continuous data, categorical data, time-varying covariates) Modeling complex and discontinuous outputs (e.g. drug dose driven by administration events) OBJECTIVE Develop a new suite of ML-based surrogate models. The intern will implement and train several promising architectures, leveraging data generated from our internal QSP models. This work will culminate in a rigorous evaluation of their performance, comparing their accuracy, training speed, and, most importantly, their flexibility in handling the complex data structures. YOU ARE A team player , a good listener, and an effective communicator Curious and proactive , ready to face real-life engineering challenges Autonomous and self-motivated with strong analytical and problem-solving skills Eager to learn mathematical modeling and simulations of biological systems Willing to explore latest advances in science and technology Responsive and capable of tackling time-sensitive issues with agility YOU WILL Review the scientific literature on relevant machine learning methods Prototype several machine learning-based surrogate models Evaluate their accuracy, training speed, and flexibility in handling complex data structures Integrate solutions into Nova's simulation platform METHODOLOGY AND TECHNICAL SKILLS We are looking for people who know some of the following or are eager to learn and work with them: Machine learning in Python, PyTorch Statistical modeling, NLME models A professional English level (written and oral) is required for this role. PRACTICAL INFORMATION Apply directly on our careers page Contact: recruitment@novainsilico.ai Salary: Competitive Start date: Flexible
Generative AI Intern — AI-Assisted Model Calibration
Nova In Silico is a health tech company that develops an in silico clinical trial platform jinkō to simulate drug efficacy and optimize clinical development using virtual patients and disease modeling. As an innovative company, we offer a dynamic work environment distinct from larger, established organizations. Interns will gain significant responsibilities and benefit from a steep learning curve, supported by a highly motivated team. KEYWORDS Generative AI, Calibration, Optimization, QSP Modeling, Mechanistic Models, Explainable AI BACKGROUND Nova In Silico is specialized in Quantitative Systems Pharmacology (QSP) Modeling, a computational approach that builds mechanistic, bottom-up models of drug-system interactions to predict outcomes in humans. Patient outcomes of treatments are evaluated by applying these models in silico to a population of virtual patients. A Virtual Population (VPop) is a set of simulated patients, each with a unique, biologically plausible parameter set, used to capture the patient-to-patient variability (heterogeneity) seen in clinical trials. A calibration strategy in QSP modeling is the methodology used to select or adjust the internal model parameters to ensure the model's output distribution accurately reflects the variability observed in clinical trial data. Defining calibration strategies for these models is currently a manual, expert-driven process that is both time-consuming and difficult to reproduce. Recent advances in Generative AI offer a promising avenue to capture expert reasoning and suggest calibration strategies automatically. This internship will explore the integration of AI into the calibration workflow, proposing strategies for which parameters to estimate, prior ranges, optimization methods, and justification of choices, optionally testing them on the Jinkō simulation engine. OBJECTIVE Develop and prototype an AI-based assistant capable of proposing calibration strategies for mechanistic or QSP models, evaluate its performance, and integrate it into the existing calibration workflow. YOU ARE A team player , a good listener, and an effective communicator Curious and proactive , ready to face real-life engineering challenges Autonomous and self-motivated with strong analytical and problem-solving skills Eager to learn mathematical modeling and simulations of biological systems Willing to explore latest advances in science and technology Responsive and capable of tackling time-sensitive issues with agility YOU WILL Review the scientific literature on hierarchical model calibration and AI-assisted reasoning Prototype AI strategies for calibration plan generation Evaluate against baseline strategies and document methods and results Integrate solutions into Nova's simulation platform METHODOLOGY AND TECHNICAL SKILLS We are looking for people who know some of the following or are eager to learn and work with them: Python LLM APIs (OpenAI, Mistral, Cohere, Anthropic) Nova's jinkō API SBML model representation standard A professional English level (written and oral) is required for this role. PRACTICAL INFORMATION Apply directly on our careers page Contact: recruitment@novainsilico.ai Salary: Competitive Start date: Flexible
QSP Modeling Intern — Oncology Therapeutics
Nova In Silico is a health tech company that develops an in silico clinical trial platform jinkō to simulate drug efficacy and optimize clinical development using virtual patients and disease modeling. As an innovative company, we offer a dynamic work environment distinct from larger, established organizations. Interns will gain significant responsibilities and benefit from a steep learning curve, supported by a highly motivated team. KEYWORDS Quantitative Systems Pharmacology, Biomodelling, Drug R D, QSP Modeling, Oncology BACKGROUND Quantitative Systems Pharmacology (QSP) is a cornerstone of modern, data-driven drug development. It utilizes mechanistic mathematical models to simulate the complex, dynamic interactions between a drug, the human body, and the disease process. At Nova In Silico, we specialize in building these high-fidelity QSP models to help de-risk and accelerate the path of new medicines to the clinic. The field of oncology, a primary focus of our work, is currently experiencing a profound revolution. The therapeutic landscape has expanded far beyond traditional small-molecule chemotherapy. We are now seeing the rise of novel therapeutic modalities, each with its own unique and highly complex mechanism of action. These include: Immunotherapies (e.g., checkpoint inhibitors, bispecific T-cell engagers) Antibody-drug conjugates (ADCs) Cell-based therapies (e.g., CAR-T) These therapies do not operate on simple "target-binding-effect" principles. Their efficacy and safety are governed by intricate, multi-scale biological processes, such as immune cell trafficking and activation, competition for target binding, tumor microenvironment interactions, and complex intracellular dynamics. To accurately predict the clinical behavior of these innovative drugs, our QSP models must evolve. Standard pharmacokinetic/pharmacodynamic (PK/PD) models are often insufficient to capture this new biology. Therefore, a critical R D objective for our team is to develop, validate, and internalize a robust library of model components specifically designed for these novel modalities. Building this internal library will enhance our platform's capabilities, allowing us to more rapidly and accurately build next-generation QSP models for our internal and client-facing projects. OBJECTIVE Contribute directly to the strategic expansion of our internal QSP model library for novel oncology therapeutics. The intern will be responsible for the end-to-end development and/or the improvement of a mechanistic model for a specific, high-priority drug class. YOU ARE A team player , a good listener, and an effective communicator: Join a growing multidisciplinary team of enthusiastic innovators Curious and proactive with a solid grounding in biology: Tackle real-life clinical challenges using knowledge in cellular and molecular biology Autonomous and self-motivated with strong analytical and problem-solving skills: Find innovative solutions to science and engineering problems Eager to learn and use mathematical methods for the modeling of biological systems: Simulate virtual diseases and treatments with ODEs, DDEs, Monte-Carlo simulations Willing to explore and exploit large datasets and virtual populations: Apply machine learning and statistical methods YOU WILL Conduct a focused literature review to identify and synthesize established mathematical frameworks, key biological mechanisms, and relevant physiological parameters Implement the new model component within our in-house QSP modeling platform jinkō Identify, extract, and curate publicly available data (e.g., from preclinical in vitro/in vivo studies or early-phase clinical trial publications) suitable for informing the model Calibrate the model by fitting it to this curated dataset, using optimization algorithms to estimate key unknown parameters Perform a thorough model evaluation and validation (e.g., perform parameter sensitivity analyses to identify key model drivers) METHODOLOGY AND TECHNICAL SKILLS We mainly use internal tools (jinkō platform) for creating the models, and R for result analysis. We are looking for people who know some of the following fields or are eager to learn and work with them: Mechanistic modeling, ODEs, PK-PD Scientific computing and statistics (R, Python) Knowledge in biology, biochemistry and/or pharmaceutical sciences Knowledge in machine learning and optimization techniques (e.g. SAEM, gradient descent) Knowledge in clinical trials and drug development A professional English level (written and oral) is required for this role. PRACTICAL INFORMATION Apply directly on our careers page Contact: recruitment@novainsilico.ai Salary: Competitive Start date: Flexible
Didn't find the role you were looking for?
We also welcome spontaneous applications for both scientific and non-scientific positions, from summer interns to seasoned veterans.
Recruitment
The whole process takes 3–4 weeks
You apply on the Nova In Silico website
You will be contacted within one week after screening of your profile.
Up to three interviews with team members
Interviews covering technical and communication skills, teamwork experience, and an opportunity to ask everything you want to know about Nova.
Meet the team onsite
When reasonably practical, we will invite you to join us for half a day to a full day at our Lyon headquarters.
Background check
We may contact your references; not mandatory, but might happen for senior positions.
Job offer
You receive our decision, and a job offer if it is positive. The contract is sent once the offer is accepted in principle.
Onboarding
Your manager contacts you to agree on a start date. Welcome to Nova. Get ready with a first week of intensive immersive training!
Ready to make an impact?
Browse our open positions or send us a spontaneous application. We'd love to hear from you.