Software Engineer, AI Systems (Canada)

Responsibilities

You will design, build, and operate multi-step LLM pipelines and agentic workflows that connect evidence bases to product experiences. This role involves managing production AI operations, including monitoring, evaluation, and technical roadmap development.

Requirements

Candidates must have extensive experience in production LLM systems, agentic workflows, and evaluation methodologies. Proficiency in Python, graph databases like Neo4j, and a strong background in deploying and monitoring enterprise-grade AI services are required.

Skills

• Python
• LLM Engineering
• Agentic Workflows
• LangGraph
• LangChain
• Neo4j
• Cypher
• Vector Search
• FastAPI
• Observability
• Azure
• Evaluation Discipline
• Retrieval Augmented Generation
• System Architecture
• Machine Learning

About this role

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.

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.

Sponsorship will not be provided for this role.  Please no agency inquiries!