2026 Intern – Algorithm Development for Enzyme Optimization

At Roche you can show up as yourself, embraced for the unique qualities you bring. Our culture encourages personal expression, open dialogue, and genuine connections, where you are valued, accepted and respected for who you are, allowing you to thrive both personally and professionally. This is how we aim to prevent, stop and cure diseases and ensure everyone has access to healthcare today and for generations to come. Join Roche, where every voice matters.

The Position

The opportunity:

We are seeking a highly motivated summer intern to support the development of algorithms for enzyme optimization within Roche Diagnostics. You will work in a hybrid setting with a multidisciplinary team of computational scientists, data scientists, and protein engineers to design, implement, and evaluate methods that improve enzyme performance for diagnostic applications.

This role is ideal for a student who enjoys working at the intersection of advanced optimization techniques, protein language models (PLMs), and molecular biology/protein engineering.

- Develop and prototype computational methods for enzyme optimization (e.g., sequence design, mutational scanning, in silico screening).

- Apply, fine-tune, and interpret protein language models (PLMs) to analyze and generate protein sequences.

- Design and implement optimization techniques (e.g., Bayesian optimization, evolutionary strategies, genetic algorithms, gradient-based or heuristic methods) to guide sequence selection and experimental design.

- Analyze sequence–function datasets from past and ongoing experiments; perform data preprocessing, feature engineering, and statistical analysis.

- Collaborate with Roche Diagnostics team members to translate biological questions into well-defined computational problems and optimization objectives.

- Document code, analyses, and models in a reproducible manner (e.g., Git, notebooks, internal reports).

- Present progress and findings to the team through brief presentations and written summaries.

Who you are:

- Currently pursuing a Master’s, or PhD in a relevant field (e.g., Computational Biology, Bioinformatics, Computer Science, Data Science, Biophysics, Molecular Biology, or related).

- Strong programming skills in Python and experience with scientific/ML libraries (e.g., NumPy, pandas, PyTorch/TensorFlow, scikit-learn, JAX).

- Good understanding of optimization techniques, such as Bayesian optimization, genetic algorithms/evolutionary strategies, reinforcement learning for black-box optimization, or related methods.

- Good understanding of protein language models (PLMs):Experience using or studying models such as ESM, ProteinMPNN, ProtTrans, or similar sequence-based representation methods.Familiarity with sequence embeddings, model fine-tuning, or downstream tasks (e.g., fitness prediction, stability/activity prediction).

- Foundational knowledge of molecular biology and protein engineering, including concepts like mutagenesis, enzyme activity, stability, and structure–function relationships.

- Strong analytical and problem-solving skills, with the ability to work autonomously between meetings in a hybrid environment.

- Good communication skills and willingness to collaborate with cross-functional, international teams.

- Coursework or research experience in molecular modeling and computational structural biology.

- Familiarity with methods for molecular docking or protein-protein/protein-ligand interaction modeling.

Preferred Qualifications:

- Prior experience with protein engineering projects, directed evolution, or sequence–function prediction models.

- Experience working with large biological sequence datasets and high-throughput screening or assay data.

- Familiarity with cloud computing environments (e.g., AWS, GCP, Azure) and/or GPU-accelerated training and inference.

- Experience using version control (Git/GitHub) and reproducible research tools (Jupyter, conda/poetry, Docker, etc.).

- Coursework or research experience in probabilistic modeling, optimization, or machine learning for biological systems.

Additional Information:

Location: Hybrid, Based in Mississauga (minimum 3 days in the office)

Hours: Full-time (35 hours per week) Internship

Length: This position is a 4 months internship (full-time 35 hours per week), and is expected to begin in May 2026.

This position is not eligible for relocation support.

#RocheInternshipCA2026

The expected salary range for this position based on the primary location of Mississauga is 57 416,00 and 75 358,50 of hiring range. Actual pay will be determined based on experience, qualifications, and other job-related factors as determined by the company.

We use artificial intelligence to screen, assess or select applicants for this role.

This posting is for an existing vacancy at Hoffmann-La Roche Ltd.

Who we are

A healthier future drives us to innovate. Together, more than 100’000 employees across the globe are dedicated to advance science, ensuring everyone has access to healthcare today and for generations to come. Our efforts result in more than 26 million people treated with our medicines and over 30 billion tests conducted using our Diagnostics products. We empower each other to explore new possibilities, foster creativity, and keep our ambitions high, so we can deliver life-changing healthcare solutions that make a global impact.

Let’s build a healthier future, together.

Roche is an Equal Opportunity Employer.