Software Engineer, Agents

Output Biosciences•New York, NY

1d•$120,000 - $250,000

About The Position

Output has built a biological reasoning model that understands biology at the scale and complexity life actually operates. Our model independently learned the principles of molecular interactions, opening up drug treatments that were previously impossible. We're already generating therapies that traditional approaches cannot reach. The hardest problems in both AI and biology are being solved here, and there is room for you to own one. Output is currently in stealth, operated by a team of repeat founders and biotech veterans with multiple exits in AI x Bio, and backed by top-tier VCs including Y Combinator. You will build the agent infrastructure that turns model capabilities into usable tools and workflows. This role owns the orchestration layer, the inference serving, the internal tooling, and the interfaces that researchers and external systems interact with.

Requirements

BS in Computer Science or a related field, or equivalent experience
4+ years of experience building production software systems
Experience integrating ML models into products or workflows, including LLM-based systems
Strong Python engineering skills with a track record of building maintainable, well-tested production code
Experience designing APIs and building systems that other engineers and researchers depend on
Comfortable with cloud infrastructure, containerization, and deployment pipelines
Think in systems: you design for reliability, observability, and graceful failure, not just the happy path

Nice To Haves

Experience with LLM orchestration frameworks, agent architectures, or tool-use patterns
Experience with MCP (Model Context Protocol) or similar model-integration protocols
Background in biology, chemistry, computational biology, or a related natural science
Experience building internal tools that accelerate research or data science teams
Experience with inference optimization for large models

Responsibilities

Design and build the agent orchestration system that composes model capabilities into multi-step workflows, handling sequencing, state management, and error recovery
Implement agent skills and tools that expose model capabilities to automated and interactive workflows
Build inference infrastructure for serving models efficiently, optimizing for latency, throughput, and reliability
Design and build APIs and integrations, including MCP-compatible interfaces, that allow external systems and users to interact with Output's models
Build internal tools that accelerate the research team's work, from experiment management to evaluation pipelines
Establish and maintain software engineering practices across the team: testing, CI/CD, code review, and documentation