North AmericaFull TimeEngineering
Remotely
pythontypescriptpostgresqldistributed systemslangchainlanggraphragopentelemetry
Job Description
📋 Description
- Design and own platform capabilities for AI agents: orchestration, retrieval, model routing, tool
- Architect retrieval systems for large-scale document collections and complex environments.
- Develop shared platform services for prompt management, caching, rate limiting, and cost
- Define stable APIs and data contracts enabling product teams to build on the platform.
- Build evaluation frameworks for accuracy, grounding, citation quality, and AI performance.
- Develop observability, tracing, and replay for troubleshooting and improvement.
🎯 Requirements
- Bachelor’s or master’s in CS/Engineering or equivalent experience.
- 7+ years building production software with end-to-end ownership.
- Proven production AI/LLM system experience, esp. retrieval-augmented generation (RAG) and agentic
- Strong Python and TypeScript proficiency.
- Solid understanding of distributed systems, asynchronous/event-driven architectures, and
- Experience owning production reliability: instrumentation, monitoring, on-call, incident response
🎁 Benefits
- Competitive CAD 126,000–175,000 per year, depending on location, experience, and alignment.
- Eligibility for an annual discretionary bonus.
- Hybrid work model with part-time office presence in Toronto, Ontario.
- Opportunity to impact high-impact AI platforms and collaborate with global teams.
- Significant technical ownership and influence over architecture and standards.
- Mentorship and professional development opportunities.