AI Engineer
About Zstate
Zstate builds domain intelligence and agentic systems with credentialed expert networks. We package training data and production agents for software engineering, healthcare, finance, and related verticals where judgment is the scarce resource.
About the role
Founding role. You build the agentic systems Zstate ships to enterprise clients: multi-step agents that use tools, retrieve context, hold state, and complete real workflows end to end. You design single-agent and multi-agent architectures, implement them with frameworks like LangChain and LangGraph, and take them from working prototype to monitored production. You work closely with the Founder and domain experts to translate a client workflow into an agent that does it reliably, then iterate using real production feedback. Reports to the Head of Engineering (currently the Founder).
What you will do
- Design and build multi-step agents using LLMs, tool use, retrieval, and memory, in frameworks like LangChain, LangGraph, or similar.
- Architect single-agent and multi-agent systems: subagents, routing and handoffs, planning, and state management for long-running tasks.
- Build evaluation frameworks for agent behaviour, including LLM-as-judge and deterministic evaluators, and use them to iterate on prompts and architecture.
- Integrate agents with client systems and data sources: APIs, databases, vector stores, and MCP or tool integrations.
- Deploy agents to production and set up observability, tracing, logging, and error analysis to monitor real-world behaviour.
- Work directly with clients and domain experts to translate a workflow into an agent spec, and iterate based on production feedback.
What we look for
- 3-8 years of experience in backend or full-stack engineering, with a track record of shipping production systems.
- 1+ years of hands-on experience in AI engineering: building agents, LLM workflows, or similar.
- Hands-on experience building agents with LLM frameworks (LangChain, LangGraph, or similar), including tool use and multi-step reasoning.
- Experience with prompt engineering and evaluation frameworks, and iterating on agent behaviour using real feedback.
- Strong proficiency in Python and/or TypeScript, APIs, and system design; cloud experience preferred.
- Comfort taking ownership of a project end to end, from architecture to a client using it in production.
- High ownership, strong execution, and the instinct to improve systems without waiting to be asked.
Nice to have
- Experience with RAG patterns, vector stores, and knowledge retrieval.
- Experience with agent observability tooling (LangSmith or similar) and debugging agent behaviour in production.
- Experience working directly with enterprise clients on technical scoping and delivery.
- Exposure to RLHF, SFT, or post-training workflows.