Senior Research Engineer (Machine Learning)

About Switchpoint Bio

Switchpoint Bio is decoding the molecular switchpoints that drive human health and disease. The choices our cells make — which genes to activate, how to respond to environment and exposure, when to mount immune defenses — are governed by epigenetic mechanisms we're only beginning to read. We bring together genomics, epigenomics, and AI to turn complex biology into decision-grade evidence for drug discovery and clinical decision-making.

The stakes are real. Epigenetics is how cells record genetics, aging, environment, and exposure across a lifetime — and it shapes nearly every major area of human disease. Our flagship programs focus on autoimmune conditions and cancer today, but the same mechanisms underlie cardiovascular, metabolic, and neurodegenerative disease. Together, these touch billions of lives — yet most treatments are still chosen by trial and error. We're building the platform that makes these mechanisms visible — and the evidence base that turns it into better drugs, earlier diagnoses, and treatments matched to the person, not the population.

Founded by pioneers in single-cell biology, epigenetics, and genomics, we operate across Helsinki and Boston. We're a small founding team in the earliest days — building not just a platform, but a company and a culture from scratch.

We hire builders. People who take ownership, move fast, and thrive when the problem is bigger than the playbook. If you want to join the first wave of hires at a company tackling some of the biggest open questions in human biology — and shape what it becomes — this is that moment. We're AI-native from day one, and we hire people who already work that way.

As a Senior Research Engineer (Machine Learning) you'll work on

• Design, train, and deploy ML models and AI systems across diverse health data — molecular data (genomics, epigenomics, proteomics), biobank cohorts, health registries, and lifestyle/exposure data. Build disease classifiers, immune cell-type identification, and foundation models that integrate these data types.
• Build agentic workflows and AI-augmented tools that multiply research output — not just assisting scientists, but doing science autonomously.
• Design and implement evaluation pipelines to benchmark model performance, safety, and generalization — you own the eval infrastructure that tells us when models are production-ready.
• Establish ML infrastructure and ops — experiment tracking, model versioning, reproducible training pipelines, cloud compute orchestration, containerized deploy
• mentsCollaborate with scientists and engineers to identify high-impact AI opportunities and ship tools that address real scientific and operational challenges.

What you'll help build in your first 12 months

• AI/ML infrastructure — work with the team to establish foundational ML systems (experiment tracking, model versioning) as you build and deploy models.
• Immune cell-type classifier — train and deploy an ML model that identifies immune cell types from sequencing data, production-ready for research and pilot projects.
• Clinical predictors — build classifiers that predict health outcomes and treatment responses from high-dimensional molecular profiles.
• Agentic research workflows — integrate AI agents into our scientific workflows to automate data analysis, hypothesis generation, and literature synthesis.
• Conversational genomics interface — implement a chat-based AI system that lets scientists and partners query and understand complex genomic and epigenomic data without writing code.

Looking to advance your Machine Learning & AI career with relocation support? Explore Machine Learning & AI Jobs with Relocation Packages that include comprehensive packages to help you move and settle in your new role.

These are real deliverables with real users. You'll own them end-to-end — from model design to deployment to iteration based on feedback.

What we're looking for

Must-have:

• Strong hands-on AI/ML building — you've trained, fine-tuned, or deployed models in production (classifiers, regressors, foundation models, agentic systems). You build and ship, not just experiment.
• Modern ML engineering — production-quality Python, cloud deployment (AWS/Azure/GCP), ML ops best practices (experiment tracking, versioning, reproducibility), containerization (Docker/Kubernetes)
• Quantitative rigor — strong foundations in probability, statistics, and linear algebra, applied to high-dimensional, noisy data. You reason about why models work and fail — batch effects, confounders, cohort generalization — and build things you can actually explain and defend.
• Evaluation rigor — you design evals that test what matters, you're honest about uncertainty, and you know the difference between a benchmark win and a result that holds up in new cohorts, new populations, and new data distributions.
• A builder's instinct — you design methods from scratch when existing tools aren't good enough, and you're not afraid of it.
• Backend and infrastructure fluency — you integrate models into applications, design APIs, deploy secure inference pipelines, and automate the boring parts.
• Clear communication across disciplines — you work effectively with biologists, engineers, and commercial partners, explain ML to non-ML people without dumbing it down, and write and speak fluent English.

Nice to have:

• Experience with high-dimensional biological or health data — omics (genomics, transcriptomics, methylation, proteomics), single-cell sequencing, biobank-scale data. You've navigated batch effects, technical artifacts, and the specific ways naive ML fails on molecular data.
• Background in genomic foundation models (e.g., AlphaGenome, Evo, Nucleotide Transformer, scGPT, Geneformer) or similar work applying transformers to biological sequences.
• Prompt engineering, RAG systems, or LLM-powered tools where they're genuinely the right tool.
• Experience with interpretability or mechanistic understanding of ML models — explaining predictions, not just making them.
• Prior work in startups, frontier labs, or research environments where you owned problems end-to-end
• Experience working in distributed, cross-timezone teams

Discover our full range of relocation jobs with comprehensive support packages to help you relocate and settle in your new location.

Why join us

• Build AI systems and infrastructure at the frontier of genomics, epigenetics, and human health
• Own systems end-to-end, from model design and evaluation to deployment and production workflows
• Help define how AI agents and modern ML workflows are integrated into scientific discovery
• Help build a company, platform, and culture from the ground up
• High ownership, autonomy, and real influence from day one
• Collaborate with globally recognized scientists and experienced team across Helsinki and Boston
• Solve meaningful problems with real-world clinical impact
• Join a lean team that moves fast and builds ambitiously
• Be part of an AI-native organization rethinking how scientific work gets done

Details

• Location: Helsinki, hybrid 2-3 days/week at company office
• Relocation: We offer relocation support for strong candidates moving to Helsinki.
• Travel: Occasional — primarily to our Boston hub, plus the occasional conference. Expect a handful of trips per year, not a monthly thing.
• Reports to: Chief Technology Officer
• Compensation: 6,500–€7,400 €/month + meaningful option package. As a first-wave hire, your option package reflects the impact you'll have on what we build.

Ready to join the team?

Apply through our recruitment system by submitting your CV or LinkedIn profile and answering a few role-specific questions in the application form. The application deadline is June 6th, 2026.