Fieldguide
AI Engineer
About this role
Fieldguide is seeking an AI Engineer to build agentic workflows that automate complex audit and advisory tasks for enterprise clients. You'll develop production-grade AI agents combining LLMs, retrieval systems, and evaluation frameworks while working at the intersection of product engineering and applied AI.
What you'll do
- Design and deploy agentic workflows that automate audit and compliance tasks
- Integrate LLMs, retrieval pipelines, and tools into reliable agent systems
- Build evaluation frameworks and feedback loops to improve agent performance
- Monitor and maintain production agents with focus on enterprise reliability
- Collaborate with product and senior engineers to translate customer needs into technical requirements
- Prototype AI solutions quickly while hardening systems for scalability
What they're looking for
- TypeScript and/or Python
- LLM API integration (OpenAI, Anthropic, Gemini)
- Agentic AI workflows and architecture
- RAG concepts and vector databases
- Production software systems
- Prompt engineering
- React and Postgres (helpful but not required)
- Problem-solving in ambiguous environments
Benefits
- Competitive compensation with equity
- Comprehensive health and wellness benefits
- Flexible time off and work schedules
- Technology reimbursements
- 401(k) plan
- Twice-yearly in-person offsites across the U.S.
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.
Fieldguide
Fieldguide builds audit and advisory software that modernizes trust and compliance for global commerce, with a focus on cybersecurity and privacy. The company is hiring Software Engineers, AI Engineers, and Production Support Engineers across all levels to design impactful features, develop agentic AI workflows, and drive system reliability.
- Website
- fieldguide.com
Likely interview questions
- Walk us through a production system you've built with LLMs or AI tooling. What went wrong, and how did you improve it?
- How would you approach building an agentic workflow to automate a complex, multi-step audit task? What challenges would you anticipate?