About Haven Safety:
Haven Safety AI is building the enterprise learning intelligence layer for safety. Co-founded with The AES Corporation and AI Fund, the venture studio founded by Andrew Ng, Haven helps high-risk organizations learn faster from what goes wrong so they can prevent what comes next.
Haven works alongside existing EHS enterprise systems to improve how organizations investigate, assess, and learn from incidents. INVESTIGATE guides evidence synthesis, timeline development, multi-threaded causal analysis, and corrective actions. ASSURE continuously reviews completed investigations for evidence quality, causal coverage, guideline adherence, and CAPA strength. LEARN reasons across incident history to surface recurring control failures, repeated corrective-action patterns, CAPA debt, and emerging signals.
The platform combines current incident evidence, company knowledge, historical cases, and an industry knowledge graph. A coordinated team of specialized AI agents examines evidence, controls, engineering factors, procedures, regulations, training, and organizational history, then produces one traceable assessment for human review. Customers have reported an 80% reduction in root cause analysis labor time using Haven.
About the Role:
You will work on the AI and LLM engineering layer that connects Haven’s evidence base and knowledge graph to the product experiences investigators and safety leaders use. This is a build-and-operate role reporting to the CTO. You will design the reasoning, ship it, instrument it, and improve it using production evidence.
The work is technically demanding and operationally consequential. Haven serves enterprise customers in regulated, safety-critical industries through multi-tenant and dedicated deployments. A plausible answer and a correct answer can look the same until someone acts on it, so precision, traceability, evaluation, and human oversight are core product requirements.
Haven Safety is a VC-backed pre-seed venture. This role will be a important member of the founding team and will require wearing multiple hats. This role is based in the US and relocation will not be considered.
What You Will Own:
- 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.
Requirements For the Role Include:
- Production LLM systems. AI or ML engineering, including shipping LLM systems that real users depend on.
- Agentic workflows. Hands-on experience building and debugging multi-step, tool-calling workflows with LangGraph, LangChain, or an equivalent framework.
- Evaluation discipline. A repeatable approach to LLM evaluation, including representative datasets, regression testing, LLM-as-judge techniques, or human review loops.
- Retrieval judgment. Experience assembling context for LLMs and a clear point of view on what to retrieve, how much, and why.
- Production ownership. 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.
- Model judgment. Comfort working across model providers and explaining tradeoffs in quality, latency, cost, context, and operational risk.
- Graph reasoning. Comfort with Neo4j and Cypher, or a comparable graph store, and the ability to ramp quickly on graph data modeling. Strongly preferred.
- Strong Python. Production habits around FastAPI, asynchronous services, testing, observability, and maintainable interfaces are required.
Nice To Haves Include:
- 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.
- B2B Enterprise SaaS. Prior experience operating in an enterprise-level environment is strongly preferred.
Why Join Haven Safety:
- Meaningful reasoning problems. Work across evidence, causal pathways, controls, organizational history, and corrective actions in a domain where correctness matters.
- An evaluation-first culture. Make quality measurable, observable, and improvable instead of relying on demos or intuition.
- Visible customer impact. Build for safety teams in energy, utilities, infrastructure, construction, and manufacturing, with direct feedback from the people using the output.
- Small team, high ownership. Work closely with the CTO, product, and knowledge engineering, make consequential technical decisions, and see your work reach customers quickly.
Skills Required
- AI or ML engineering experience, including shipping production LLM systems used by real users
- Hands-on experience building and debugging multi-step, tool-calling agentic workflows using LangGraph, LangChain, or an equivalent framework
- Repeatable LLM evaluation approach using representative datasets, regression testing, LLM-as-judge methods, or human review loops
- Experience assembling retrieval context for LLMs and making informed decisions about what and how much to retrieve
- Track record owning systems through deployment, monitoring, and incident response, including diagnosing and fixing failures or regressions
- Comfort working across multiple model providers and explaining quality, latency, cost, context, and operational-risk tradeoffs
- Comfort with Neo4j and Cypher or a comparable graph store, plus ability to learn graph data modeling
- Strong Python production practices, including FastAPI, asynchronous services, testing, observability, and maintainable interfaces
- Deep graph experience, including Cypher, schema evolution, MERGE patterns, embeddings, and operating a live knowledge graph
- Enterprise AI security experience, 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 similar platforms
- Prior experience operating in a B2B enterprise SaaS environment
- Must be based in the United States; relocation will not be considered
AI Fund Compensation & Benefits Highlights
The following summarizes recurring compensation and benefits themes identified from responses generated by popular LLMs to common candidate questions about AI Fund and has not been reviewed or approved by AI Fund.
-
Healthcare Strength — Health coverage is portrayed as strong with great healthcare and dental coverage, plus vision insurance, long-term disability, and life insurance. Feedback suggests this aligns with tech-standard benefits for US roles at a small venture studio.
-
Retirement Support — Retirement benefits include a 401(k) plan with employer match for US employees. Feedback suggests this forms part of a competitive total package for fund roles.
-
Parental & Family Support — Family support includes fully paid parental leave for applicable roles. Feedback suggests this is a standout benefit for an organization of this size.
AI Fund Insights
What We Do
Who is AI Fund? We are a team of AI pioneers, proven entrepreneurs, seasoned operators, and venture capitalists that collaborates with leading entrepreneurs to solve big challenges using artificial intelligence. Founded in 2017 by Dr. Andrew Ng, AI Fund is backed with $176 million in capital by some of the leading VC firms and investors, including NEA, Sequoia, and Greylock. How Are We Different? We work with entrepreneurs during their startup’s most critical and risky phase, from 0 to 1. At the earliest stages, your company strategy is still being formed, and you’re still on the path to demonstrating your idea’s full potential – this is a reality we understand. This is the period when decisions on product strategy, market fit, and team are most critical, moving fast and fixing parts of your business when you have limited resources is a challenge. We believe the best way to help entrepreneurs is by providing our time, expertise, and resources to help flesh out these key strategic decisions. Making the right decisions at the right time can often make the difference. We are here to improve these dynamics, at a time when the help matters the most. Why Work With AI Fund? Getting a startup from idea to Series A funding is not easy. We’ve been there and understand the challenges you must overcome. Whether you desire limited help and just want access to our unique ecosystems of AI experts and entrepreneurs or you would like our full support, we are interested in the opportunity to help in your success. We are flexible in how we work with companies, but ultimately, we are here to maximize your chance of success and accelerate getting your company to market. We provide the capital, expertise, and resources to accelerate the work required to minimize risks in your startup, help you rise above the noise, and make your company more attractive to new investors.
