Machine Learning (ML) Engineer – AI & Bioinformatics

ProQR Therapeutics NV; Leiden; On-site; EUR 90,000 - 130,000; Full time

Benefits offered by this job

Annual performance bonus

Stock options

premium-free pension plan

Commuting allowance

Unlimited healthy snacks and drinks

Employee events

Job summary

ProQR Therapeutics NV in Leiden, the Netherlands, seeks an experienced ML Engineer - AI & Bioinformatics to join our R&D team. You will build scalable ML pipelines, transform biology data into AI-ready datasets, and support both scientific modeling and automation of bioinformatics workflows.

You will work with lab scientists and bioinformaticians to ensure data-model alignment, contribute to data infrastructure, and apply machine learning to RNA therapeutics challenges.

Qualifications

• MSc in Computer Science, Data Science, or a related quantitative discipline.
• At least 2 years of relevant work experience in machine learning, Generative AI models, Deep learning, or data engineering.
• Strong proficiency in Python for data processing, scripting, and model development.
• Experience with JAX or PyTorch for training and evaluating machine learning models.
• Basic understanding of molecular biology and willingness to learn RNA editing concepts.
• Hands-on experience with Linux-based environments and command-line tools.
• Familiarity with Docker (preferred) or similar containerization tools.
• Knowledge of software engineering best practices, including version control (Git), modular code design, and documentation.
• Exposure to R for statistical workflows.
• Curiosity and adaptability to explore the best tools and approaches for each project.

Responsibilities

• Design editing oligonucleotide (EON) candidates using ML models in a lab-in-the-loop cycle.
• Develop, train, and evaluate AI models using JAX or PyTorch for biological prediction and design tasks.
• Adapt and fine-tune foundation models for downstream tasks; explore new architectures.
• Benchmark model performance across diverse biological tasks and contribute to model selection.
• Collaborate with wet-lab teams to plan design-test-learn rounds.
• Design, build, and maintain modular, reproducible data pipelines.
• Automate and optimize data flows using scripting and containerized tools like Docker.
• Collaborate cross-functionally with domain scientists and project leads.
• Contribute to data infrastructure initiatives, including FAIR schema development.
• Support statistical analyses and data exploration using Python and/or R.
• Ensure reproducibility through modular code design, Git, and thorough documentation.
• Engage in technical discussions and knowledge-sharing sessions.

Skills

MSc in Computer Science

2+ years ML experience

Python proficiency

JAX or PyTorch

Linux command line

Git/version control

R knowledge

Docker familiarity

Curiosity and adaptability

Education

MSc in Computer Science, Data Science, or related

Tools

JAX

PyTorch

Docker

Git

R

Job description

Department R&D

ProQR Therapeutics is a NASDAQ-listed biotechnology company headquartered in Leiden, the Netherlands with an office in and Cambridge, Massachusetts, USA. At ProQR, we are on a mission to edit RNA, treat disease and change lives. A team of 180+ enthusiastic ProQRians from all walks of life and more than 30 different nationalities is committed to pioneering transformative RNA therapies to make a difference in the lives of the communities we serve.

Our proprietary Axiomer™ RNA editing technology platform enables the editing of specific single nucleotides in RNA using the cells own editing machinery. Axiomer RNA editing technology harnesses ADAR (Adenosine Deaminase Acting on RNA), a protein which is present in all human cells, to repair G-to-A mutations, modulate protein, and enable protective mutation functions. Axiomer could potentially yield a new class of innovative medicines and treat currently untreatable diseases. By harnessing the power of RNA editing, we aim to create a world where genetics inform your health - but never limit it.

Our R&D department is currently looking for an experienced ML Engineer - AI & Bioinformatics to join our team in Leiden. The ML Engineer will contribute to the development of robust, scalable pipelines that transform complex experimental biology data into AI-ready datasets. This role supports both scientific modeling initiatives and the automation of critical bioinformatics workflows, contributing to a standardized and reproducible data infrastructure.

This position is ideal for someone with a strong foundation in machine learning and data engineering who is eager to apply those skills to real-world biological challenges and data-driven decision-making. You will work closely with laboratory and computational scientists, bioinformaticians and domain experts to ensure seamless integration of data and models.

We expect our ML Engineer to have:

• MSc in Computer Science, Data Science, or a related quantitative discipline


• At least 2 years of relevant work experience in Machine learning, Generative AI models, Deep learning, or Data engineering (industry or advanced academic research)


• Strong proficiency in Python for data processing, scripting, and model development


• Practical experience with JAX or PyTorch for training and evaluating machine learning models


• Basic understanding of molecular biology plus willingness to learn RNA editing and oligonucleotide concepts on the job


• Hands-on experience with Linux-based environments and command-line tool.


• Familiarity with Docker (strongly preferred) or similar containerization tools for reproducible environments


• Demonstrated experience or interest in handling biological datasets Knowledge of software engineering best practices, including version control (Git), modular code design, and documentation


• Exposure to R for statistical workflows


• Curiosity and adaptability to explore the best tools and approaches for each project

Preferred:

• Experience with foundation models, such as pre-training, fine-tuning, or applying large sequence models (biological or otherwise)


• Experience with active learning, Bayesian optimization, or other sequential experimental design methods

Key Responsibilities:

• Design editing oligonucleotide (EON) candidates using ML models in a lab-in-the-loop cycle: propose sequences for synthesis and testing, incorporate the new experimental results, and iteratively improve both the models and the designs


• Develop, train, and evaluate AI models using JAX or PyTorch for biological prediction and design tasks in RNA therapeutics


• Adapt and fine-tune foundation models for downstream tasks, and explore new architectures and methods from literature


• Benchmark model performance across diverse biological tasks and contribute to model selection and improvement


• Work with wet-lab teams to plan design-test-learn rounds, including selecting which candidates to test so each round is as informative as possible


• Design, build, and maintain modular, reproducible data pipelines that transform raw experimental data into standardized, AI-ready datasets


• Automate and optimize data flows to reduce manual steps and improve scalability, using scripting and containerized tools (e.g., Docker)


• Collaborate cross-functionally with domain scientists, bioinformaticians, and project leads to align computational outputs with experimental context


• Contribute to data infrastructure initiatives, including FAIR-compliant schema development, metadata standards, and platform integration


• Support statistical analyses and data exploration using Python and/or R


• Ensure reproducibility through modular code design, version control (Git), thorough documentation, and adherence to best practices


• Engage in technical discussions, retrospectives, and team knowledge-sharing sessions to foster learning and continuous improvement

Skills and competencies that are required for making the difference:

• Analytical and accurate


• Creative thinker


• Flexible and adaptable


• Hands-on mentality


• Proactive and pragmatic self-starter, with a result-oriented mindset


• Team player


• Autonomous and coachable


• Being able to work in a fast-paced environment


• Being able to prioritize multiple tasks


• Patient-oriented attitude


• Excellent knowledge of spoken and written English

ProQR as an employer

As an employer, we value a diverse workforce in which people are encouraged to develop themselves both personally and professionally. We believe that when people are happy, energized and supported by an environment in which they can thrive, they can achieve extraordinary things.

We are committed to ensuring that no employee, candidate, or job applicant receives less favorable treatment on the grounds of race, age, disability, pregnancy, religion, gender identity and expression, sexual orientation, marriage or civil partnership status. At ProQR we want to create an inclusive culture where everyone can be valued for who they are and in which individual differences and contributions in all forms are recognized and valued.

We offer an exciting and innovative working environment in a very committed organization, with the following benefits:

• An annual performance bonus


• Stock options


• premium-free pension plan


• A commuting allowance


• Unlimited (un) healthy snacks and drinks


• Employee events (boot camp, Coffee and Collaboration Café and other social events)

We are looking for people who are inspired by our mission to edit RNA, treat disease and change lives. Are you up for the challenge?

We are an innovative biotech company headquartered in Leiden, the Netherlands. We focus on the development of life-changing RNA therapies for severe rare and common diseases. Are you up for a challenge?

ProQR was founded by Daniel de Boer with a mission to help people living with rare genetic diseases. This remains the sole focus of our company today.

Our passion lies in discovering the latest RNA technologies and translating them to life-changing treatments for people with severe rare and common diseases.