Senior AI Engineer - Core
Hilbert's AI7 hours ago
Base Salary
$170k - $190k/yr
Responsibilities
- Own evaluation and testing for production agents, including evaluation harnesses, metrics, golden datasets, regression gates, and human review.
- Architect and implement agent workflows with state memory, routing, tool registries, recovery paths, and human-in-the-loop checkpoints.
- Build and operate systems from experimentation through production, including tracing, monitoring, latency management, cost-per-task budgeting, and on-call support.
- Diagnose production failures such as hallucinations, tool misuse, retrieval misses, and silent degradation, converting them into durable fixes and tests.
- Develop intelligent retrieval strategies combining RAG, graph-based retrieval, chunking, embeddings, ranking, and grounding.
- Integrate agents with external platforms so they can execute workflows and take real-world actions.
- Set technical standards for agent development, review designs, define reusable patterns, and communicate technical tradeoffs across the team.
- Make pragmatic engineering decisions under ambiguity and collaborate closely with founders and cross-functional partners.
Requirements
- 6+ years of production software engineering experience building APIs, services, or data infrastructure.
- 2+ years building LLM or agent systems that shipped to production and were used by real users.
- Hands-on experience with LangChain, LangGraph, or equivalent agent and orchestration frameworks.
- Experience owning production code with tests, CI/CD, and on-call responsibilities.
- Clear communication skills for explaining technical decisions and debating architecture tradeoffs.
- Strong ownership, judgment, and ability to work effectively in ambiguity and at startup speed.
- Preferred experience with deep RAG systems, including hybrid and graph retrieval, chunking, embeddings, ranking, and grounding.
- Preferred experience with LLM observability, Langfuse, OpenTelemetry, and cost or latency optimization.
- Preferred experience with MCP, tool-calling frameworks, structured output, and constrained decoding.
- Early-stage startup or high-growth company experience is a plus.
Benefits
- 100% coverage of employee health, dental, and vision premiums, with dependent or spouse coverage available at additional cost.
- 401(k) through Human Interest with an immediately vested employer match.
- Generous paid time off.
- Commuter cost support for San Francisco-based employees.
- Lunch vouchers through DoorDash at the San Francisco office.
- Based in San Francisco with occasional travel for team meetings, offsites, or customer engagements.
Categories
About Hilbert's AI
Hilbert is a scalable, data science-first growth infrastructure that gives B2C teams predictive clarity into user behavior, revenue drivers, and the actions that drive sustainable growth. Backed by a16z, Asylum Ventures, and more. Fully agentic by design, Hilbert shrinks months-long decision cycles to minutes. One Infrastructure. Four Intelligence Layers. Built for Momentum. Hilbert turns fragmented data into clear answers and decisive actions using a proprietary architecture of AI/ML algorithms accessible through natural language. No code, no dashboards, no guesswork.