Benchling
Agentic AI Engineer
About this role
Benchling seeks a founding Agentic AI Engineer to design and build production-grade agentic AI systems that power the company's R&D platform. You'll own the technical architecture, build reliable systems on modern foundation models, and enable teams across the organization to leverage AI workflows at scale.
What you'll do
- Define foundational architecture for enterprise agentic AI including orchestration, frameworks, tool integrations, and observability
- Write and ship production code for agentic systems at least 50% of the time, building CI/CD and evaluation infrastructure
- Design systems with enterprise security controls: multi-tenant isolation, audit logging, RBAC, and human-in-the-loop safeguards
- Graduate prototypes from discovery into hardened production systems and own operational support
- Coach internal teams and power users on production patterns and best practices for agentic AI
- Lead technical hiring and ideation for the founding AI systems team
What they're looking for
- Production systems engineering with modern foundation models
- Agentic AI architecture and orchestration frameworks
- Enterprise security and multi-tenant system design
- CI/CD, testing, and observability for AI systems
- Python or systems programming languages
- API integration and tool orchestration
- Technical leadership and mentoring
- Cloud infrastructure and deployment patterns
Benefits
- Remote work, US-based
- Founding engineer role with significant technical autonomy
- Hands-on engineering culture with 50%+ coding responsibility
- Partnership with AI Product Manager and cross-functional teams
- Opportunity to shape AI systems strategy at scale
Opens the application — the Jobs AI extension fills it for you. Set up autofill
Opens the official application on the employer’s site. No login required.
Benchling
Benchling builds an AI-powered platform for biotech R&D that integrates scientific workflows and data processes to accelerate research breakthroughs. The company is hiring software engineers across full-stack, customer engineering, agentic AI, and security roles to enhance developer productivity, build production AI systems, and protect sensitive research data.
- Website
- benchling.com
Likely interview questions
- Walk us through a production system you've built using LLMs or AI agents. How did you approach reliability, observability, and handling failure modes?
- Describe your experience with agent frameworks and orchestration tools. What trade-offs have you made between building custom vs. using existing platforms like LangChain or CrewAI?