Software Engineer, AI Systems (Canada)

Location: Canada; remote

Company

hirify.global is a VC-backed pre-seed venture building an enterprise learning intelligence platform for safety-critical organizations, alongside The AES Corporation and AI Fund.

What you will do

• Build and operate multi-step LLM pipelines coordinating model calls, tools, graph queries, retrieval, quality gates, and specialist-agent handoffs.
• Extend the agent orchestration layer that moves incidents from evidence through analysis, review, and enterprise learning.
• Design grounding and hybrid retrieval across Neo4j graph traversal, vector search, and organizational knowledge.
• Build evaluation datasets, scoring systems, regression suites, model comparisons, and human-review loops.
• Implement tracing, tool-call audits, cost and latency monitoring, failure handling, and quality dashboards.
• Select models across OpenAI, Anthropic, and Google while shaping the AI roadmap with product and knowledge engineering.

Requirements

• Production AI or ML engineering experience, including LLM systems used by real users.
• Hands-on experience building and debugging multi-step, tool-calling workflows with LangGraph, LangChain, or an equivalent framework.
• Experience with repeatable LLM evaluation, representative datasets, regression testing, LLM-as-judge methods, or human review loops.
• Strong retrieval judgment and experience assembling effective LLM context.
• Ownership of deployed systems through monitoring and incident response, including diagnosing and fixing failures or regressions.
• Strong Python and production experience with FastAPI, asynchronous services, testing, observability, and maintainable interfaces.

Nice to have

• Strong Neo4j and Cypher experience, graph data modeling, schema evolution, MERGE patterns, embeddings, and live knowledge graph operations.
• Experience with prompt-injection protection, context-leak prevention, tenant isolation, role-based access, and policy-layer separation.
• Experience with Azure, Azure AI Search, Pinecone, MongoDB Atlas, pgvector, Elasticsearch, or similar platforms.
• Background in B2B enterprise SaaS.

Culture & Benefits

• Work on safety-critical reasoning problems involving evidence, causal pathways, controls, organizational history, and corrective actions.
• Evaluation-first engineering focused on measurable, observable, and improvable quality.
• Direct customer impact for safety teams in energy, utilities, infrastructure, construction, and manufacturing.
• Small founding team with high ownership and close collaboration with the CTO, product, and knowledge engineering.
• Visa sponsorship is not provided.