AI Engineer
The Bio protocol is a financial layer for Decentralized Science (DeSci), engineered to commercialize scientific research more quickly. It enables anyone to fund, develop, and govern tokenized scientific innovations from various sources. The platform is built on a growing ecosystem of DeSci projects and is supported by key figures in both the crypto and biotech industries.
About BIO Protocol
Bio Protocol is a decentralized science (DeSci) platform that serves as a financial layer to commercialize scientific research more quickly. It enables anyone to fund, develop, and govern tokenized scientific innovations from universities, companies, and researchers globally. The platform features Ignition Sales for backing promising research through low-cap fundraises, a BioXP point system for earning access to these sales through staking and governance, and a platform for building on Bio's Scientific AI Agents. The ecosystem supports various DeSci projects in specialized therapeutic areas like longevity, women's health, psychedelic science, and more, with backing from top crypto and biotech players.
Skills
About the Role
You will design, build, and scale agent systems for planning, tool use, memory, and context management. You will integrate agents with internal and external tools and data sources, implement safety guardrails and sandboxed execution, and develop evaluation, telemetry, and automated scoring systems. You will instrument data pipelines for fine-tuning and reinforcement learning, profile and optimize performance and reliability, and contribute to platform services, APIs, orchestration, CI/CD, and observability.
Requirements
- Experience building production software in Python or TypeScript
- Strong systems and API design skills (FastAPI, gRPC, GraphQL or similar)
- Proven experience shipping LLM applications or agentic systems including tool use, function calling, retrieval/RAG, structured outputs, evaluation, or observability
- Familiarity with agent and orchestration frameworks (LangChain, LangGraph, AutoGen, CrewAI, MCP) and vector databases (FAISS, Weaviate, Pinecone)
- Experience with cloud infrastructure and containers (AWS, GCP, or Azure), Docker, Kubernetes, Terraform, CI/CD, and production telemetry
- Ability to translate research prototypes into robust, scalable systems
- Experience with fine-tuning and reinforcement learning (RL, RLAIF, RLHF) — nice to have
- Familiarity with benchmarks and evaluations and with schema, ontology, and provenance design — nice to have
Responsibilities
- Build agent capabilities for planning, tool use, memory, and context management and ship them into production
- Integrate agents with internal and external tools and data sources using robust schemas and safeguards
- Develop quality and evaluation systems including unit tests, regression tests, scenario benchmarks, telemetry, and automated scoring
- Collaborate with scientists to analyze failure modes and improve performance
- Ensure outputs are source-traceable and compliant with provenance standards
- Implement safety measures, guardrails, and sandboxed execution for risky operations
- Optimize performance and reliability via profiling, idempotency, retries, rate limiting, and uptime management
- Instrument data pipelines for supervised fine-tuning and reinforcement learning
- Contribute to agent platform services, APIs, orchestration, CI/CD, and observability