Senior Research Engineer

About the role

This is not a general full-stack or product engineering role, you'll live in the AI layer full-time: prompts, agents, retrieval, evaluation, and model behavior, embedded inside product squads building an AI-powered product that is transforming how clinical trials are run. You'll move fast, prototype early, and help set technical direction for how our embedded AI Engineers work, mentoring more junior teammates along the way.

This is an exciting opportunity to join a fast-paced biotech AI startup at an early stage of its growth, as we continue expanding our US presence.

Key Responsibilities

• Design, prototype, and ship the AI-specific parts of product features, prompts, agents, tool integrations, and retrieval
• Build and refine tool-calling and multi-step agent workflows for product-specific use cases
• Design and maintain evaluation frameworks and golden datasets for our AI systems
• Build automated pipelines for prompt and context optimization
• Monitor and improve model quality, latency, and cost in production, diagnosing regressions using evals and telemetry
• Integrate platform and model capabilities into end-to-end product experiences
• Design and implement guardrails, safety checks, and fallback behavior for AI features in production
• Debug complex issues in model and agent behavior, from prompt/tool-call traces to unexpected outputs
• Evaluate and apply retrieval-augmented generation, fine-tuning, and other techniques where they fit a product need
• Partner closely with product and design to translate user needs into AI-driven technical solutions
• Provide fast, direct feedback to the Platform and AI Scientist teams based on real-world AI usage patterns
• Mentor junior AI Engineers and help set technical standards for AI-specific work across product initiatives

Must-haves

• Degree in Computer Science, with a specialization or concentration in Machine Learning (or equivalent depth gained on the job)
• 5+ years of experience working directly on AI/ML-powered systems
• Full working exposure across the modern AI stack: LLM APIs, prompt engineering, agent frameworks, tool calling, RAG/retrieval, embeddings, and evaluation practices
• Solid grounding in core ML fundamentals (model behavior, training vs. inference, failure modes) even if your day-to-day is applied rather than research
• Experience designing or running evaluation frameworks and automated prompt-optimization pipelines for ML or LLM-based systems
• Experience integrating LLM APIs and reasoning about their operational tradeoffs (latency, cost, context limits, failure modes)
• Track record of shipping AI-powered, user-facing features end-to-end
• Experience designing and implementing guardrails or safety checks for AI systems
• Comfort debugging model and agent behavior, not just application code
• Experience mentoring or leading other engineers