AI Engineer

About the role

You will design and deliver the core agent systems that enable Bio Protocol to coordinate AI and human scientists toward safe, verifiable scientific outcomes. You will own the end to end lifecycle of agent capabilities, from initial prototype to production scale, ensuring they are reliable, observable, and aligned with research workflows. You will translate high level scientific goals into concrete agent behaviors, balancing performance with rigorous safety constraints. You will work hand in hand with domain experts to ensure that every agent action is grounded, traceable, and auditable. Your contributions will directly influence how AI participates in hypothesis generation, experimental planning, and data interpretation. If you care about building durable, principled systems rather than short lived demos, this role is for you.

Key facts

What you'll do

• 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 (retrieval systems, structured datasets, lab/biomed APIs, spreadsheets, search), with robust schemas and safeguards.
• Develop quality and evaluation systems, including unit, regression, and scenario/benchmark tests, telemetry, and automated scoring.
• Collaborate with scientists to analyze failure modes and improve performance.
• Partner with the knowledge and 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 through 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, including services, APIs, orchestration, CI/CD, and observability.

Example projects first 90 days

• Deliver a multi tool agent capable of executing long horizon scientific tasks with memory and self correction, supported by regression tests and telemetry.
• Implement automated citation enforcement, including source checking, freshness validation, and 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.

Requirements

• Experience building production software in Python and or TypeScript, with strong systems and API design skills (FastAPI, gRPC, GraphQL, or similar).
• Proven experience shipping LLM applications or agentic systems (tool use/function calling, retrieval/RAG, structured outputs, evaluation, or 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, or Azure), Docker/Kubernetes/Terraform, CI/CD, and production telemetry.
• Ability to translate research prototypes into robust, scalable systems.
• Strong written and verbal communication to collaborate effectively with interdisciplinary teams.
• Comfort working in a fast moving, mission driven environment where priorities evolve based on scientific needs.
• Willingness to engage deeply with life sciences domain experts to ensure technical solutions address real research problems.

Nice to have

• Experience with fine tuning and reinforcement learning (RL, RLAIF, RLHF), including reward design and offline evaluation.
• Familiarity with benchmarks and evaluations such as SWE Bench, OS World, or tau bench.
• Knowledge of retrieval and knowledge systems, including schema and ontology design, entity modeling, and provenance tracking.
• Background in agentic system safety and security (sandboxing, isolation, permissions, auditability).
• Exposure to life sciences or scientific computing and collaboration with domain experts.

Practical notes

• Remote location with no travel required.
• Full time engagement.
• No visa sponsorship information provided.
• No explicit compensation details listed in this posting.
• No specific application deadline mentioned; interested candidates are encouraged to apply directly.

This role is ideal for a hands on engineer who wants to shape the infrastructure that connects AI with rigorous scientific discovery, and who values traceability, safety, and real world impact above all else. If you are motivated by difficult technical constraints and the opportunity to work at the intersection of AI and biotechnology, Bio invites you to submit your application and join our mission of directing capital and capability toward scientifically meaningful outcomes.