Biotech ML Scientist Jobs & Internships 2026
Biotech ML scientists apply machine learning to accelerate drug discovery, protein structure prediction, genomics analysis, and clinical trial optimization — fields where AI has demonstrated transformative impact. AlphaFold's solution to the protein structure prediction problem was a landmark moment, inspiring a generation of researchers to bring ML methods into biology. Companies like Recursion and Insitro are building drug discovery platforms where ML models guide experimental design, dramatically accelerating the traditional timeline from target identification to clinical candidate.
What Does a Biotech ML Scientist Do?
Biotech ML scientists develop deep learning models that predict protein-ligand binding affinity to identify drug candidates from virtual libraries of billions of compounds. They analyze genomic sequencing data with specialized ML architectures to identify disease-associated variants and gene expression patterns that reveal biological mechanisms. Image analysis of high-content screening data — processing millions of microscopy images to quantify cell morphology changes induced by drug candidates — is a major application area. They build patient stratification models that identify subpopulations most likely to respond to specific therapies, making clinical trials more efficient. Generative models for de novo molecule design — generating novel molecular structures with desired properties — represent the frontier of computational drug discovery.
Required Skills & Qualifications
- ✓Computational drug discovery: molecular property prediction with graph neural networks
- ✓Genomics analysis: variant calling, RNA-seq differential expression, and GWAS interpretation
- ✓Protein structure prediction and docking using AlphaFold2 and molecular dynamics
- ✓High-content imaging analysis: cell morphology quantification from fluorescence microscopy
- ✓Bioinformatics tooling: Bioconductor, scanpy, PyMol, and RDKit
- ✓Deep learning for biological sequences: protein language models and genomic foundation models
- ✓Clinical trial design optimization and patient stratification using ML
- ✓Python scientific computing for biological data: BioPython, pandas, and matplotlib
A Day in the Life of a Biotech ML Scientist
Morning begins reviewing results from an overnight virtual screening run — a GNN-based binding affinity model has scored 10 million compounds from a virtual library and identified 500 high-confidence candidates for a target kinase. After selecting the top 50 for synthesis prioritization based on predicted ADMET properties, you attend a cross-functional sync with medicinal chemists to walk through the candidates and discuss synthetic accessibility. Late morning involves fine-tuning a cell morphology model on a new cell line dataset from a partner lab, evaluating whether the existing model generalizes or requires retraining. Afternoon is spent on collaborative analysis with a genomics colleague, building a multi-omics integration model that combines transcriptomics and proteomics data to identify novel disease biomarkers.
Career Path & Salary Progression
Computational Biology Intern → ML Scientist I → Senior ML Scientist → Principal Scientist → VP of Computational Research
| Level | Base Salary | Total Comp (with equity) | Intern Monthly |
|---|---|---|---|
| Intern | — | — | $8,000–$13,000/mo |
| Entry-Level (0–2 yrs) | $115,000–$170,000 | +20–40% in equity/bonus | — |
| Mid-Level (3–5 yrs) | $170,000–$238,000 | +30–60% in equity/bonus | — |
| Senior (5–8 yrs) | $238,000–$332,000 | +50–100% in equity/bonus | — |
Salary data sourced from Levels.fyi, Glassdoor, and company disclosures. 2026 estimates.
Top Companies Hiring Biotech ML Scientists
Genentech
Moderna
Recursion
Insitro
BenevolentAI
Apply for Biotech ML Scientist Roles
Submit your profile and a PropelGrad recruiter will help you land an interview for biotech ml scientist internships and entry-level positions at top companies.
Biotech ML Scientist — Frequently Asked Questions
What biology background do biotech ML scientists need?
Substantial biology domain knowledge is expected. Understanding the central dogma of molecular biology, how drugs interact with targets, what genomic data represents, and how drug discovery programs work is essential context for building relevant models. Engineers who invest in this background — through coursework, reading, and collaboration with biologists — build significantly better tools. Many biotech ML scientists hold PhDs in computational biology, bioinformatics, or biochemistry.
What is Recursion and what makes their approach to drug discovery unique?
Recursion uses AI and high-content cellular imaging to build a biological foundation model trained on massive databases of cellular perturbation experiments. Rather than targeting a single disease, they're building a general 'map of biology' that guides drug discovery across many disease areas simultaneously. Their industrialized approach — running millions of experiments robotically to generate training data — is fundamentally different from traditional computational drug discovery.
How has AlphaFold changed biotech ML engineering?
AlphaFold2 and AlphaFold3 have made highly accurate protein structure prediction available to every researcher, eliminating a major bottleneck in structure-based drug design. ML scientists now use predicted structures as inputs for docking calculations, binding site identification, and protein engineering. The broader impact has been to validate that AI can solve core biology problems, driving massive investment in AI drug discovery platforms.
What is the typical educational background for biotech ML scientists?
A PhD in computational biology, bioinformatics, machine learning, or a closely related field is common for scientist-level positions. Some companies hire ML engineers with strong biological knowledge and title them as research engineers. Master's-level candidates can enter as research associates. The combination of deep ML skills and biological fluency is rare and highly valued.
What is the difference between a biotech ML scientist at Genentech vs. at Recursion?
Genentech (a Roche subsidiary) is a large pharmaceutical company with established drug pipelines — ML scientists support specific programs with computational analysis and predictive modeling. Recursion is an AI-first company building a platform to discover drugs — ML scientists work on foundational capabilities of the discovery platform itself. Genentech offers more stability and resources; Recursion offers faster innovation cycles and direct involvement in building the ML platform.