Lead AI Back-End Engineer

This is a fully remote position, open to applicants in Canada.

📋 Description

• Establish the technical architecture for a platform driven by agents, utilizing LLMs, retrieval technologies, agent frameworks, and microservice patterns.

• Lead the design of high-throughput APIs employing .NET, C#, Python 3.11+, FastAPI async, SQLModel, and Semantic Kernel.

• Oversee multi-agent orchestration, including handoff, sequential, parallel, and supervisory patterns.

• Direct the implementation of Retrieval Augmented Generation on platforms such as Azure AI Search, pgvector, Chroma, and similar technologies.

• Manage complete CI/CD pipelines, which encompass linting, type checking, security scanning, testing, containerization, and deployment.

• Mentor and recruit engineers while integrating AI coding agents like Cursor and Claude Code.

• Advocate for observability and FinOps for LLM workloads through structured JSON logging, OpenTelemetry tracing, Langfuse, evaluation frameworks, and cost dashboards.

• Collaborate with Product and Security teams to align business objectives, compliance needs, AI capabilities, and user feedback into a comprehensive technical roadmap.

• Guide the foundational intelligence behind AI products that cater to millions of users, ensuring reliability, security, governance, and economic standards.

⛳️ Requirements

• A minimum of 7 years in building and scaling production backend systems.

• At least 2 years in a technical lead, staff, principal, or comparable position.

• Proficient in designing and developing REST APIs with Python FastAPI or .NET C# APIs.

• Extensive experience with dependency injection, middleware, profiling, performance optimization, and distributed systems.

• Proven hands-on leadership experience with Semantic Kernel or similar agent and LLM frameworks.

• Practical experience in agent orchestration, tool calling, structured outputs, and multi-step workflows.

• Completed at least one production RAG system or pipeline using a vector or hybrid search platform such as Azure AI Search, pgvector, Chroma, or similar.

• In-depth expertise in PostgreSQL along with SQLModel, SQLAlchemy 2, and Alembic migrations at scale.

• Experience in integrating various advanced and cost-optimized model providers, including model routing, structured output, reasoning, tool calling, and fallback strategies.

• Proficient with tools such as Poetry, Docker, GitHub Actions, Azure DevOps, Jenkins, or Argo.

• Familiarity with infrastructure as code concepts and blue-green or canary release strategies.

• Strong leadership capabilities through code reviews, architectural guidance, technical mentoring, roadmap planning, hiring, and cross-team collaboration.

• Preferred: experience with message queue and event-driven architectures using RabbitMQ, Kafka, Azure Service Bus, or similar technologies.

• Preferred: knowledge of GPU inference fleets, self-hosted open-weight models, or serverless model hosting.

• Preferred: understanding of model gateways, intelligent model routing, MCP, agent interoperability, prompt caching, and LLM cost optimization.

• Preferred: familiarity with automatic evaluation pipelines, agent evaluations, LLM-as-judge techniques, safety guardrails, and cost-aware prompt and context engineering.

🏝️ Benefits

• Work-life balance.

• Diversity and inclusion programs.

• Learning and development opportunities.

• 20+ affinity groups for networking and connection.

• Competitive HMO benefits – 175k MBL with one free dependent after one year of service.

• Punctuality Bonus.

• Generous vacation policy.

• Mentoring and career growth opportunities.