Note: The job is a remote job and is open to candidates in USA. Haven Safety AI is building an enterprise learning intelligence layer for safety that helps high-risk organizations investigate incidents, assess evidence, and learn from recurring failures. The Software Engineer, AI Systems will build and operate production LLM reasoning systems, agent orchestration, retrieval, evaluation, and AI operations for safety-critical enterprise applications.
Responsibilities
- Production reasoning systems. Build and operate multi-step LLM pipelines that coordinate model calls, tool calls, graph queries, retrieval, quality gates, and specialist-agent handoffs
- Agent orchestration. Extend Haven’s coordinated agent team and the orchestration layer that carries an incident from evidence through analysis, review, and enterprise learning
- Grounding and retrieval. Design the context layer across Neo4j graph traversal, vector search, and hybrid retrieval so every model call receives the right evidence and organizational knowledge
- Evaluation. Build datasets, scoring, regression suites, model comparisons, human-label loops, and per-stage quality attribution for extraction and reasoning tasks
- Production AI operations. Implement tracing, tool-call audits, cost and latency monitoring, failure handling, and quality dashboards; catch loops, hallucinations, and silent drift before customers do
- Technical direction. Select models by task across OpenAI, Anthropic, and Google; partner with product and knowledge engineering; and help shape the AI roadmap
Skills
- 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 what to retrieve, how much, and why
- A track record of owning systems from deployment through monitoring and incident response, including a strong story about a failure or regression you diagnosed and fixed
- Comfort working across model providers and explaining tradeoffs in quality, latency, cost, context, and operational risk
- Comfort with Neo4j and Cypher, or a comparable graph store, and the ability to ramp quickly on graph data modeling
- Production habits around FastAPI, asynchronous services, testing, observability, and maintainable interfaces are required
- Deep graph experience. Cypher fluency, schema evolution, MERGE patterns, embeddings, and operating a live knowledge graph
- Enterprise AI security. Prompt-injection awareness, context-leak prevention, tenant isolation, role-based access, and policy-layer separation
- Azure and hybrid search. Experience running production AI services in Azure and using Azure AI Search, Pinecone, MongoDB Atlas, pgvector, Elasticsearch, or a similar platform
- Prior experience operating in an enterprise-level environment
Benefits
- Remote work arrangement
Company Overview
Company H1B Sponsorship