Senior ML Engineer – Agentic AI

About the role

You will join Kaiko’s ML Engineering team building the agentic system, the software harness that turns powerful models into something clinicians can rely on in real workflows.

In healthcare, this matters more than anywhere else. Doctors don’t need another interface that produces fluent text. They need a system that supports structured clinical thinking and collaboration, synthesizes messy context, makes uncertainty explicit, and produces artifacts that can be inspected, discussed, and improved with expert feedback.

As a Senior ML Engineer, you will design, ship, and evaluate the harness components that make our agentic system safe and effective. You’ll contribute to reliability, evaluation, and the engineering that brings agents into clinical practice.

You’ll be based in Zurich or Amsterdam, with an expectation to spend around half your time in the office.

• Context lifecycle management from intent to verified, persistent outputs
• Tools and integrations across internal systems and external data sources
• Durable memory and state that support long-running, multi-step clinical work
• Evaluation and verification loops that reduce drift, context loss, and hallucinations

• Strong Python skills and solid Git collaboration experience (PRs, branching, code review)
• Experience building LLM-driven features such as prompt and context design, RAG-based retrieval and grounding, tool use, and practical failure handling
• Experience building agents with a clear view of what makes them succeed or fail including state management, planning and execution tradeoffs, tool reliability, and guardrails
• Experience with at least one agentic framework such as Lang Chain, Auto Gen, or similar, or experience building custom production-ready agentic systems
• Strong ML foundation with particular strength in transformers and how LLMs and VLMs behave in practice including capabilities, limitations, and evaluation
• Experience designing evaluation for LLM and agentic systems including deterministic test suites, scenario-based evaluations, and rubric-based or LLM-as-judge approaches
• Clear communicator comfortable with design discussions, code review, and cross-functional collaboration

• Experience with knowledge graphs or structured representations for reasoning and retrieval
• Experience using workflow orchestration tools such as Dagster or similar
• Familiarity with distributed execution frameworks (e.g., Ray) and scaling workloads cleanly
• You stay up to date with the latest developments and literature on agentic systems and can turn new ideas into shippable engineering
• Some experience with Reinforcement learning

• An attractive and competitive salary, a good pension plan and 25 vacation days per year.
• Great offsites and team events to strengthen the team and celebrate successes together.
• A EUR 1000 learning and development budget to help you grow.
• Autonomy to do your work the way that works best for you, whether you have a kid or prefer early mornings.
• An annual commuting subsidy.