Agentic AI Engineer

Benchling is building Intelligence Engineering & Enablement, a new team within Security & IT focused on enterprise agentic AI systems. As the founding Agentic AI Engineer, you'll own the technical architecture, production systems, and cross-functional enablement for AI agents and orchestration at scale—bridging rapid prototyping with hardened, governed production deployments.

About the Role

This is a senior individual contributor position on a flat team where you'll act as a player-coach: hands-on engineering most of the time, setting technical direction, and driving hiring and mentorship. You'll partner closely with an AI Product Manager on prioritization and with peers on data foundations, while building reliable production systems around modern foundation models rather than training models from scratch. It's early days for enterprise agentic AI at Benchling, and you'll move fast—iterating prototypes, learning from internal customers, and evolving with the field.

Responsibilities

• Define foundational architecture for enterprise agentic AI—orchestration, agent frameworks, tool integrations (including MCP), memory and state management, evaluation, and observability—with clear build vs. buy decisions and documented rationale.
• Write production code at least half your time, especially in year one. Build CI/CD, testing, evaluation, and deployment infrastructure for agentic systems; graduate prototypes into hardened, production-grade systems; own production support under a "you build it, you run it" model.
• Design for enterprise security and compliance from day one: multi-tenant isolation, secrets management, audit logging, payload encryption, role-based access controls, and human-in-the-loop controls. Partner with Security Engineering on threat modeling for agentic architectures—prompt injection, tool misuse, data exfiltration.
• Enable builders across the company by coaching power users and departmental teams on production patterns, developing criteria for graduating prototypes to enterprise systems, and building developer experience (templates, SDKs, sandboxes) for safe shipping.
• Partner across functions with Data, Analytics & Systems teams on source-of-truth datasets and pipelines; engage department leaders on transformed workflows; and collaborate with platform and infrastructure teams to leverage existing capabilities.
• Elevate engineering standards in code quality, testing and evaluation, documentation, and on-call practices. Drive technical hiring through interview design and bar-raising. Mentor engineers on the team and other AI builders across the company.

Requirements

• 7+ years of professional software engineering building production systems with strong systems design fundamentals.
• Hands-on production experience integrating LLMs and/or agentic patterns: orchestration, tool use, memory and state management, evaluation, and observability.
• Demonstrated ability to optimize across deterministic and non-deterministic capabilities, balancing architecture to the needs of specific solutions.
• Production experience with at least two of: Python, TypeScript/Node.js, Go; comfortable working across the stack.
• Hands-on expertise with LLM APIs (OpenAI, Anthropic), agentic frameworks (LangChain, CrewAI), RAG over business content (Confluence, contracts, policies), vector databases (pgvector, Pinecone), workflow automation (n8n, Langflow), and LLM observability and evaluation tooling (LangSmith, Arize).
• Track record of building from zero to one: a platform, function, or product area you scaled from scratch.
• Experience in regulated or security-sensitive environments. Solid grasp of enterprise security fundamentals—encryption, access controls, audit logging, secrets management.
• Comfortable exercising technical leadership independent of positional authority; set direction, raise the bar in design reviews, and grow other engineers through influence.
• Product-first engineering mindset: ship code quickly and care about real-world impact.
• Strong communication with technical and non-technical audiences; translate workflows into engineering plans and engineering tradeoffs into business language.
• Interest in learning about life science (prior knowledge not required).

Nice to Have

• Background in enterprise SaaS, life sciences, or biotech.
• Familiarity with LLM orchestration patterns and frameworks (LangGraph, MCP, agent SDKs from major model providers).
• Experience with async orchestration (Temporal, Prefect, Airflow) applied to long-running or agentic workflows.
• Familiarity with SOC 2, HIPAA, or GxP compliance as applied to AI systems.
• Experience building internal developer platforms or internal tools at scale.
• Direct experience coaching or enabling non-engineers (analysts, ops staff, business power users) to build with AI tooling.
• Based in or willing to relocate to San Francisco, CA (relocation assistance offered).

Benefits & Work Arrangement

Flexible hybrid work with expectation of on-site collaboration 3 days per week (Monday, Tuesday, Thursday) in San Francisco, CA. Open to remote candidates, though strong preference for San Francisco-based or willing-to-relocate candidates.