Senior AI Systems Engineer - Production LLM & Graph Reasoning

AI Fund; United States; On-site; USD 180,000 - 240,000; Full time

Job summary

Haven Safety AI is building the enterprise learning intelligence layer for safety and is seeking an experienced AI/LLM engineer to design, ship, and operate production-grade reasoning systems that connect evidence bases to product experiences used by investigators and safety leaders.

In this build-and-operate role reporting to the CTO, you will own multi-step LLM pipelines, agent orchestration, grounding of evidence, evaluation pipelines, and production AI operations in a regulated enterprise

Qualifications

• Production LLM systems shipped in production environments.
• Agentic workflows: building multi-step, tool-calling workflows.
• Evaluation discipline with datasets and regression testing.
• Retrieval judgment for context selection.
• Production ownership from deployment to monitoring and incident response.
• Model judgment across providers and tradeoffs in quality, latency and cost.
• Graph reasoning with Neo4j and Cypher.
• Strong Python production habits (FastAPI, async, testing).
• Deep graph experience with embeddings and knowledge graphs.
• Enterprise AI security and policy controls.
• Azure and hybrid search experience.

Responsibilities

• Production reasoning systems: Build and operate multi-step LLM pipelines coordinating model calls, tool calls, graph queries, retrieval, quality gates, and agent handoffs.
• Agent orchestration: Extend Haven’s coordinated agent team and orchestration layer for incident progression from evidence to enterprise learning.
• Grounding and retrieval: Design the context layer across Neo4j traversal, vector search, and hybrid retrieval for accurate evidence grounding.
• Evaluation: Build datasets, scoring, regression suites, model comparisons, human-label loops, and per-stage quality attribution.
• Production AI operations: Implement tracing, tool-call audits, cost and latency monitoring, failure handling, and quality dashboards; catch loops and drift.
• Technical direction: Select models by task across OpenAI, Anthropic, and Google; shape AI roadmap.

Skills

Production LLM systems

Agentic workflows

Evaluation discipline

Retrieval judgment

Production ownership

Model judgment

Graph reasoning

Strong Python

Deep graph experience

Enterprise AI security

Azure and hybrid search

Tools

Neo4j

Cypher

LangGraph

LangChain

Azure AI Search

Pinecone

MongoDB Atlas

pgvector

Elasticsearch

Job description

Haven Safety AI is building the enterprise learning intelligence layer for safety and is seeking an experienced AI/LLM engineer to design, ship, and operate production-grade reasoning systems that connect evidence bases to product experiences used by investigators and safety leaders.

In this build-and-operate role reporting to the CTO, you will own multi-step LLM pipelines, agent orchestration, grounding of evidence, evaluation pipelines, and production AI operations in a regulated enterprise