At a glance
- Employment
- Full-time
- Workplace
- Remote
- Location
- Remote
About the role
- This is a build-and-operate role reporting to the CTO, focusing on the AI and LLM engineering layer that connects Haven’s evidence base and knowledge graph to product experiences.
- The role involves designing, shipping, instrumenting, and improving reasoning systems using production evidence within a VC-backed pre-seed venture.
- As a founding team member, the engineer will work on technically demanding, operationally consequential systems for safety-critical industries.
Responsibilities
- Build and operate multi-step LLM pipelines coordinating model calls, tool calls, graph queries, retrieval, quality gates, and specialist-agent handoffs.
- Extend Haven’s coordinated agent team and the orchestration layer for incident analysis and enterprise learning.
- Design the context layer across Neo4j graph traversal, vector search, and hybrid retrieval.
- Build datasets, scoring, regression suites, model comparisons, human-label loops, and per-stage quality attribution.
- Implement tracing, tool-call audits, cost and latency monitoring, failure handling, and quality dashboards.
- Select models by task across OpenAI, Anthropic, and Google.
- Partner with product and knowledge engineering to shape the AI roadmap.
Requirements
- Experience in AI or ML engineering, including shipping LLM systems that real users depend on.
- Hands-on experience building and debugging multi-step, tool-calling workflows with LangGraph, LangChain, or an equivalent framework.
- A repeatable approach to LLM evaluation, including representative datasets, regression testing, LLM-as-judge techniques, or human review loops.
- Experience assembling context for LLMs and a clear point of view on retrieval strategies.
- A track record of owning systems from deployment through monitoring and incident response.
- Comfort working across model providers and explaining tradeoffs in quality, latency, cost, context, and operational risk.
- Strong Python skills with production habits around FastAPI, asynchronous services, testing, observability, and maintainable interfaces.
- Deep graph experience including Cypher fluency, schema evolution, MERGE patterns, embeddings, and operating a live knowledge graph.
- Knowledge of enterprise AI security including prompt-injection awareness, context-leak prevention, tenant isolation, role-based access, and policy-layer separation.
- Experience running production AI services in Azure and using Azure AI Search, Pinecone, MongoDB Atlas, pgvector, Elasticsearch, or a similar platform.
Preferred qualifications
- Comfort with Neo4j and Cypher, or a comparable graph store, and the ability to ramp quickly on graph data modeling.
- Prior experience operating in an enterprise-level B2B SaaS environment.
Skills
- Python
- FastAPI
- LLMs
- LangGraph
- LangChain
- Neo4j
- Cypher
- Azure
- Azure AI Search
- Pinecone
- MongoDB Atlas
- Pgvector
Show all 15 skills
- Elasticsearch
- OpenAI
- Anthropic
