Base Salary
$176k - $265k/yr
Responsibilities
- Define the foundational architecture and technical direction for enterprise agentic AI, including orchestration, agent frameworks, tool integrations, memory and state management, evaluation, and observability.
- Write production code at least half the time during the team’s first year and build the infrastructure for testing, evaluation, deployment, and production support.
- Graduate prototypes into hardened, governed, production-grade systems under a you-build-it-you-run-it operating model.
- Design for multi-tenant isolation, secrets management, audit logging, payload encryption, role-based access controls, and risk-calibrated human-in-the-loop controls.
- Partner with Security Engineering on threat modeling for prompt injection, tool misuse, and data-exfiltration risks.
- Create templates, SDKs, sandboxes, and production patterns that enable departmental teams and internal AI builders.
- Partner with Data, Analytics & Systems on source-of-truth datasets and pipelines and collaborate with platform and infrastructure teams.
- Set standards for code quality, testing, evaluation, documentation, and on-call practices.
- Lead ideation, planning, delivery, technical hiring, interview design, candidate representation, and mentoring while people management remains with the hiring manager.
Requirements
- 7+ years of professional software engineering experience building production systems with strong systems design fundamentals.
- Hands-on production experience integrating LLMs and/or agentic patterns, including orchestration, tool use, memory and state management, evaluation, and observability.
- Production experience with at least two of Python, TypeScript/Node.js, and Go, with comfort working across the stack.
- Hands-on expertise with LLM APIs including OpenAI and Anthropic; agentic frameworks including LangChain and CrewAI; RAG over business content; vector databases including pgvector and Pinecone; workflow automation including n8n and Langflow; and observability and evaluation tools including LangSmith and Arize.
- Track record of building and scaling a platform, function, or product area from scratch.
- Experience in regulated or security-sensitive environments and knowledge of encryption, access controls, audit logging, and secrets management.
- Technical leadership experience independent of positional authority, including setting direction, leading design reviews, and mentoring engineers.
- Product-first approach, strong ownership, rapid delivery, and effective communication with technical and non-technical audiences.
- Interest in learning more about life science; prior life-science knowledge is not required.
- Nice-to-have experience in enterprise SaaS, life sciences, or biotech.
- Nice-to-have familiarity with LangGraph, MCP, major model-provider agent SDKs, Temporal, Prefect, Airflow, SOC 2, HIPAA, GxP, internal developer platforms, and enabling non-engineers to build with AI tooling.
Benefits
- Flexible hybrid work arrangement with in-office collaboration expected 3 days per week: Monday, Tuesday, and Thursday.
Tech Stack
Categories
About Benchling
We are rebuilding biotech for the AI era. When a breakthrough is delayed, the world waits. Getting a molecule from discovery to patients, or a crop from lab to field, involves thousands of slow, manual, disconnected steps. AI has the potential to change this, compressing decades of R&D work into years. But that only happens when clean, structured scientific data and AI are built into how science gets done. Benchling is the AI platform for biotech R&D. Scientists use Benchling to design experiments, capture structured data, and run AI agents and models directly in their workflows. Over 200,000 scientists around the world trust Benchling to power their most important work, from academic labs to Sanofi, Moderna, and more than half of the world's top 50 biopharma.