Research Engineer, Agents
Boltz · London
Bio & Science AIremote
At a glance
Highlights
- Build agent harnesses powering AI molecular modeling research pipelines.
- Scale large agent swarms on cluster with observability and verification.
- Turn frontier models into production tools used by Top 20 pharma.
What they offer
- Highly competitive salary with meaningful equity
- 25 days plus bank holidays a year
- Annual team offsite trip
- Private healthcare (BUPA), covering pre-existing conditions
- Pension program
- Paid parental leave
- Wellhub gym membership
- Free lunch every day
- Travel expenses
Ideal candidate
Strong systems engineer who has built widely adopted agent systems and has sharp intuition for frontier LLM capabilities and failure modes. Rigorous about correctness and excited to build research tooling without needing an ML research background.
Requirements
- Strong software engineering experience, including distributed systems or infrastructure that runs many long-running jobs in parallel and handles failures
- Experience building agent systems or harnesses (tool use, orchestration, context and state management, evaluation) that you can discuss in depth
- Good judgment about the capabilities and failure modes of frontier LLMs, and about keeping agent-produced work correct and maintainable
- A track record of building tools that were widely adopted by researchers or engineers
- Experience developing open-source agent harnesses or extending existing ones
- Understanding of LLM architectures, and experience fine-tuning LLMs with SFT or reinforcement learning
- Background in NLP or information retrieval, such as search, ranking, embeddings or RAG
- Experience running workloads on a shared compute cluster or cloud infrastructure (e.g. Kubernetes)
- Exposure to scientific research workflows
- Experience using Boltz models
- hiring process
- Initial screen with Talent team, diagnosis interview working through a degraded training run, onsite in London or virtual onsite, then offer and onboarding.
Lab profile
About Boltz
Building AI-powered molecular modeling tools to make biology programmable and accelerate drug discovery.
What they build
- Boltz-1 open-source structure prediction model
- AI-powered molecular modeling tools
- Boltz Lab
Known for
- AlphaFold 3-level accuracy for biomolecular complexes
- Fully open-source and commercially available models
- Broadly accessible frontier capabilities
Posted · Last seen