Strong vibe-coding focus: building agentic workflows with LangChain/LangGraph, RAG, vector DBs, and LLM-driven integrations for fast iteration and real-world action.
About the Role
Lead AI Engineer to own the technical direction and delivery of Hilbert's agentic AI stack, building production-grade systems that perform multi-step inference across enterprise data silos. Hands-on role combining coding, architecture, and engineering leadership to ship reliable, evaluated, and integrated agent workflows for enterprise customers.
Job Description
Role
Lead the design, development, and evolution of Hilbert’s AI systems. Own the AI stack end-to-end, ship production-grade agentic features and pipelines, set technical direction in partnership with founders, and grow the engineering team while remaining hands-on in the code.
Key Responsibilities
-
Build — hands-on, every day
- Design, build, and maintain AI-driven features and pipelines that serve enterprise customers at scale
- Architect and implement agent-based workflows using LangChain, LangGraph, or equivalent orchestration frameworks
- Own critical systems end-to-end from experimentation through production deployment and monitoring
- Build and improve evaluation pipelines to measure, validate, and iterate on AI system performance
- Make pragmatic engineering decisions under ambiguity — ship, learn, iterate
-
Lead — set direction and raise the bar
- Define and own the technical roadmap for the AI stack
- Make architecture and infrastructure decisions balancing short-term speed and long-term scalability
- Establish engineering standards for code quality, reviews, testing, documentation, and deployment discipline
- Prioritize ruthlessly and communicate technical strategy and tradeoffs to technical and non-technical stakeholders
-
Grow — build the team and the culture
- Hire, mentor, and develop AI engineers as the team scales
- Create an environment of ownership, intellectual honesty, and high-velocity shipping
- Run effective processes (standups, reviews, retros) without bureaucracy
Requirements
- Strong Python engineer with clean, testable, production-ready code and an active coding practice
- Deep experience with LangChain, LangGraph, or equivalent agent/orchestration frameworks at scale
- Proven ability to own AI systems end-to-end, including deployment, monitoring, and evaluation
- Product-minded engineering leadership: align technical direction with business outcomes
- Excellent communication skills and experience aligning teams and explaining tradeoffs to non-technical stakeholders
- Comfortable operating in high-autonomy, high-ambiguity startup environments and setting tempo for the team
Strong Pluses
- Experience building evaluation pipelines and defining metrics that predict real-world performance
- Backend software engineering experience (APIs, services, data infrastructure, production systems)
- Exposure to retrieval-augmented generation (RAG), vector databases, or LLM-powered search and recommendation systems
- Prior experience as a tech lead, engineering manager, or founding engineer at an early-stage or high-growth company
- Track record of hiring and developing engineers
Current Hurdles
- Defining intelligent retrieval across heterogeneous approaches (RAG, vector DBs, graph-based retrieval)
- Designing agentic workflows that handle edge cases, missing data, escalation to humans, and graceful degradation
- Building systematic, reproducible evaluation processes that predict real-world performance
- Architecting integration layers for agents to take action and execute workflows with human-in-the-loop checkpoints
Location & Compensation
- Location: San Francisco, US
- Compensation: Competitive salary + equity; specific compensation details shared in later steps
Hiring Process
Short form intro call → Technical working session → Team conversations → Offer