Hilberts
AI Engineer - Core
- Confirmed live in the last 24 hours
- $140k–$170k
- Mid level
- Full-time
- Remote · San Francisco
- 4+ yrs exp
- Added 3 weeks ago
About this role
Hilbert is seeking an AI Engineer to build and improve their demand intelligence platform, focusing on agentic workflows and production-grade AI systems. This role centers on owning the evaluation layer for their agents, ensuring changes improve performance and addressing real-world production failures. The ideal candidate will thrive in a fast-paced startup environment and possess a strong understanding of agent architectures and LLM systems.
What you'll do
- Own the evaluation layer for agents, including harnesses and regression gates.
- Architect and implement agent workflows using LangChain or similar frameworks.
- Diagnose and resolve production failures such as hallucinations and retrieval misses.
- Contribute to setting technical standards for agent development.
- Collaborate with the founding team and cross-functional partners.
What they're looking for
- LangChain
- LangGraph
- LLM Systems
- Agent Architectures
- Production Software Engineering
- Evaluation Harnesses
- RAG (Retrieval-Augmented Generation)
- Observability (Langfuse, OpenTelemetry)
Benefits
- Startup Culture
- Ownership and Urgency
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.
Hilberts
- Industry
- Technology & Software
Likely interview questions
- Describe a time you had to debug a production issue with an LLM-powered application. What was your approach?
- Explain your experience with LangChain or LangGraph. What are some limitations you've encountered?