Benchling
Agentic AI Engineer
About this role
Benchling seeks a founding Agentic AI Engineer to design and build enterprise-grade AI agent systems across the company. You'll own the technical architecture, build production systems around foundation models, and establish patterns that enable both internal teams and departmental AI initiatives.
What you'll do
- Define foundational architecture for enterprise agentic AI including orchestration, agent frameworks, tool integrations, and observability
- Write production code at least 50% of the time, shipping early portfolio of agentic systems from prototype to hardened production
- Build CI/CD, testing, evaluation, and deployment infrastructure for agentic systems with full SDLC rigor
- Design for enterprise security from day one: multi-tenant isolation, audit logging, role-based access controls, and human-in-the-loop safeguards
- Enable builders across the company through coaching, standards, and shared infrastructure for departmental AI solutions
- Partner with AI Product Manager on prioritization and Data team on data foundations for agentic systems
What they're looking for
- AI systems engineering and production deployment of foundation model applications
- Software architecture design (orchestration, frameworks, integrations, state management)
- Full-stack backend development and CI/CD infrastructure
- Enterprise security practices (audit logging, secrets management, threat modeling)
- AI observability and evaluation frameworks
- Technical leadership and mentoring
- Prompt engineering and agent design patterns
- Cross-functional collaboration and stakeholder management
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 around foundation models or LLMs. How did you approach reliability, observability, and handling failures?
- Describe your experience building or architecting agentic systems. What frameworks or orchestration approaches have you used, and what trade-offs did you consider?