AI Engineer
Bio · Remote
About this role
## AI Engineer — Bio Protocol (AI Agents) ### About Bio Bio is a decentralized science protocol that helps launch and grow AI-driven biotech research. It enables scientists to raise funds, create value from their work, and distribute that value directly to their communities. Since 2023, Bio has directed over **$50M** to global researchers—backed by investors including **Binance Labs**, **Northpond Ventures**, and **Animoca Brands**—to accelerate real-world therapeutics across longevity, brain health, fertility, psychedelic science, and more. ### Why this role exists As a **Member of Technical Staff** on the **AI Agents** team, you’ll design, build, and scale the core agent systems that power Bio Protocol’s products. You’ll partner with full-stack engineers and scientist-evaluators to create agents that can plan, use tools, and reason safely—helping shape how AI collaborates with human scientists. ### What you’ll do - Build agent capabilities for **planning**, **tool use**, **memory**, and **context management**, and ship them into production. - Integrate agents with internal/external tools and data sources (retrieval systems, structured datasets, lab/biomed APIs, spreadsheets, search) with **robust schemas** and **safeguards**. - Develop **quality and evaluation systems**: unit/regression/scenario & benchmark tests, telemetry, and automated scoring. - Collaborate with scientists to analyze **failure modes** and improve performance. - Work with the knowledge/ontology team to 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 when needed. - Contribute to the agent platform: services, APIs, orchestration, CI/CD, and observability. ### Example projects (first 90 days) - Deliver a multi-tool agent for long-horizon scientific tasks with memory + self-correction, supported by regression tests and telemetry. - Implement automated citation enforcement (source checking, freshness validation, provenance display in the UI). - Build an evaluation dashboard tracking competency pass rates, latency, and failure modes. ### Success metrics - Improved pass rates and reduced critical error rates across core scientific competencies. - Performance against SLOs for latency, task success, tool-call reliability, and uptime. - Increased coverage of regression and evaluation scenarios. - Broader adoption of the agent platform by internal teams. ### Qualifications - Experience building production software in **Python and/or TypeScript**, with strong systems and API design skills (e.g., **FastAPI, gRPC, GraphQL**). - Proven experience shipping **LLM applications / agentic systems** (tool use/function calling, retrieval/RAG, structured outputs, evaluation, observability). - Familiarity with agent/orchestration frameworks (e.g., **LangChain, LangGraph, AutoGen, CrewAI, MCP**) and vector databases (**FAISS, Weaviate, Pinecone**). - Experience with cloud infrastructure and containers (**AWS/GCP/Azure**), **Docker/Kubernetes/Terraform**, **CI/CD**, and production telemetry. - Ability to translate research prototypes into robust, scalable systems. ### Nice to have - Fine-tuning and reinforcement learning experience (**RL, RLAIF, RLHF**) includin
Listing freshness
CronJobs last confirmed this listing 2h ago. If its source stops confirming the opening for seven days, this page is removed from active inventory.