Leads the team this role joins
Heads the group this role sits in
In-house, owns the opening
From your own Gmail and LinkedIn.
About the role
This is a fully remote, full-time role for an engineer on Bio Protocol's AI Agents team, who will design, build and scale the agent systems behind its products. Bio Protocol is a decentralized science protocol that funds AI-driven biotech research, and the role works closely with full-stack engineers and scientist evaluators. The work covers planning, tool use, memory and safe reasoning, with outputs that must stay traceable to their sources.
What you’ll do
- Build agent capabilities for planning, tool use, memory and context management, and ship them to production.
- Connect agents to retrieval systems, structured datasets, lab and biomedical APIs, spreadsheets and search, with clear schemas and safeguards.
- Build evaluation systems with unit, regression and benchmark tests, telemetry and automated scoring.
- Work with scientists to analyze failure modes and improve performance.
- Partner with the ontology team to keep outputs source-traceable and compliant with provenance standards.
- Add guardrails and sandboxed execution for risky operations.
- Improve performance and reliability through profiling, retries, rate limiting and uptime work.
- Contribute to the agent platform, including services, APIs, orchestration, CI/CD and observability.
What they’re looking for
- Experience building production software in Python or TypeScript with strong systems and API design skills.
- Proven experience shipping LLM applications or agentic systems, including tool use, retrieval, structured outputs or evaluation.
- Familiarity with agent and orchestration frameworks such as LangChain, LangGraph, AutoGen, CrewAI or MCP.
- Experience with vector databases such as FAISS, Weaviate or Pinecone.
- Cloud, container and infrastructure experience across AWS, GCP or Azure, including Docker, Kubernetes, Terraform and CI/CD.
- The ability to turn research prototypes into robust, scalable systems.
Nice to have
- Fine-tuning and reinforcement learning experience, including reward design and offline evaluation.
- Familiarity with benchmarks such as SWE-Bench, OS-World or tau-bench.
- Knowledge of retrieval and knowledge systems, including schema, ontology, entity modeling and provenance tracking.
- Background in agent safety and security, such as sandboxing, isolation and auditability.
- Exposure to life sciences, scientific computing or collaboration with domain experts.
What’s on offer
- Fully remote work from anywhere.
- Competitive compensation with a token and equity component.
- A small team with direct impact on AI-driven biology.
Skills
Questions about this role
Is this role remote?
Yes, the listing says fully remote, work from anywhere.
Does it pay in equity?
The posting mentions a token and equity component alongside competitive compensation.
Do I need life sciences experience?
No, life sciences exposure is listed as nice to have.