Build production LLM services in Downtown Toronto using Python, Go, and modern AI coding assistants within a hybrid engineering team. This full-time role centers on enterprise AI platform development.
As a Senior AI Engineer, you will design, ship, and run services used across a global financial services company. You will build agents with Anthropic, OpenAI, or Google SDKs, connect models through Azure OpenAI or AWS Bedrock, and deploy services on Kubernetes. The work spans prototypes through production debugging.
Key Responsibilities: Build Python and Go services calling enterprise LLM platforms
Own data models, logic, APIs, and Kubernetes deployments
Create evaluation pipelines and test sets for model outputs
Monitor LLM cost, latency, tracing, and output quality




Design secure multi-tenant permissions, authentication, and usage limits
Requirements: Six or more years of qualified software engineering experience
Recent production LLM development experience
Daily use of Claude Code, Copilot, or Cursor
Strong Python or Go with agent SDK experience
Skills in prompting, tool calling, structured outputs, and context management
Apply senior software engineering judgment to production LLM services, Kubernetes delivery, evaluation, and secure enterprise AI development.

#J-18808-Ljbffr

📌 Senior LLM Platform Engineer Toronto (Ontario)
🏢 Encore Technical Solutions
📍 Ontario