We are looking for a Lead Python AI Engineer to build robust, AI-powered API services and agentic workflows. In this role, you will bridge the gap between traditional backend systems and modern language models, focusing on secure and scalable LLM interactions with internal systems, vector databases, and external tools via orchestration frameworks.
We treat LLMs not as magic, but as components in a secure, scalable distributed system. If you take pride in API reliability, graceful failure handling, and production-grade AI integration, we’d love to talk to you.
Req# The recruiting efforts for this position are intended to fill an existing vacancy for a current position.
ResponsibilitiesEnd-to-End Ownership: Own API contracts and service reliability end-to-end. AI edge cases must fail gracefully without compromising system integrityRigorous Systems Engineering: Integrate LLMs with a strong engineering foundation—baking in evaluation, comprehensive observability, robust fallback handling, and cost awarenessReusable Frameworks: Build reliable, reusable orchestration frameworks and logic designed for downstream developer consumptionDesign and build scalable backend API services and advanced LLM orchestration layersImplement and maintain complex RAG (Retrieval-Augmented Generation) pipelines, covering document ingestion, chunking, embedding, and retrieval optimizationDevelop and connect agent tools using LangChain, LangGraph, and potentially MCP (Model Context Protocol)Ensure top-tier security, privacy, enterprise-grade observability,



and comprehensive test coverage across all backend workflowsContribute actively to architecture decisions and engineering standards within your podCollaborate cross-functionally with frontend engineers, data engineers, and infrastructure teamsRequirementsBackend

Experience:
7+ years of backend engineering with a heavy focus on microservices and distributed systems, using Python for high-performance backend services and cloud-native APIsCloud & Infrastructure: Hands-on experience with AWS, Docker, ECS/EKS, and RESTful APIsSecurity First: Proven experience with secure coding practices and strong authentication/authorization (auth/authz) fundamentalsAgentic Frameworks: Practical, hands-on experience with frameworks such as LangChain, LlamaIndex, or LangGraphAI SDK Integration: 1–2+ years of hands-on experience integrating AI SDKs (OpenAI, Anthropic/Claude, AWS Bedrock, or equivalent) in production environmentsAI Observability & Evaluation: Familiarity with AI evaluation tooling or real-time APM platforms (e.g., LangSmith, Langfuse, Arize)RAG Pipelines: Practical experience working with vector databases (e.g., Amazon Kendra, OpenSearch), advanced embedding strategies, and retrieval systemsNice to haveFrontend Fluency: 1–2+ years of experience with React and TypeScriptScale & Deployment: Experience deploying applications to EKS environments at scaleInteroperability & Security: Knowledge of agent interoperability patterns (MCP) and identity/security domain models (IAM, CIAM)Secondary Languages: Professional proficiency in Java, Node.js, or GoWe offerExtended Healthcare with Prescription Drugs, Dental and Vision, and Healthcare Spending

📌 Lead Python AI Engineer (Canada)
🏢 EPAM Systems
📍 Canada