Sr. GenAI Python Developer

**This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a Sr. GenAI Python Developer based in Canada.** This role offers the opportunity to design and build advanced artificial intelligence solutions that move from experimentation to real-world production impact. You will work on cutting-edge GenAI initiatives involving large language models, retrieval-augmented generation, vector databases, and AI agent frameworks. The position combines hands-on software engineering, rapid prototyping, and collaboration with product and technical teams to solve complex business challenges. You will help shape AI engineering practices, develop scalable solutions, and accelerate the adoption of emerging technologies. Working within a highly skilled and collaborative environment, you will have the freedom to explore innovative ideas while delivering measurable outcomes. This is an ideal opportunity for an experienced Python developer passionate about transforming AI concepts into reliable enterprise solutions. ### Accountabilities: The Sr. GenAI Python Developer will play a key role in designing, developing, and productionizing AI/ML solutions. You will collaborate with engineers, product stakeholders, and technical leaders to rapidly validate ideas, establish best practices, and deliver scalable AI-powered applications. - Design, develop, and deploy AI/ML solutions that evolve from proof-of-concept experiments into production-ready systems. - Build advanced GenAI applications using large language models, retrieval-augmented generation (RAG), vector databases, and agentic frameworks. - Develop Python-based applications, APIs, pipelines, and AI orchestration workflows. - Partner with product and engineering teams to rapidly iterate on prototypes, incorporate feedback, and improve solutions. - Establish strong AI engineering practices, including design patterns, testing strategies, code quality standards, and development guidelines. - Implement prompt engineering techniques, structured outputs, model evaluations, and strategies to reduce hallucinations and improve reliability. - Design and optimize RAG architectures, including data ingestion pipelines, chunking strategies, indexing, similarity search, and metadata filtering. - Develop AI agent workflows, including multi-agent collaboration patterns and tool integrations. - Implement Model Context Protocol (MCP) patterns, including MCP servers, tool endpoints, and integrations with AI applications. - Support AI solutions in production through monitoring, troubleshooting, performance improvements, and reliability enhancements. - Use development acceleration tools to improve productivity and speed up software delivery. - Collaborate effectively with technical and non-technical stakeholders to communicate solutions, trade-offs, and business value. ## Requirements: The ideal candidate is an experienced AI-focused software engineer with strong Python expertise, a passion for emerging technologies, and the ability to transform innovative concepts into scalable applications. You should combine deep technical skills with strong problem-solving and communication abilities. - Minimum of 10 years of professional Python development experience. - Minimum of 4 years of experience working on AI projects, particularly focused on delivering production-ready AI/ML solutions. - Advanced Python programming skills with experience building APIs, pipelines, and AI-driven applications. - Strong understanding of machine learning fundamentals and practical application in AI solution development. - Hands-on experience with Generative AI technologies, including: - Retrieval-Augmented Generation (RAG). - Fine-tuning approaches. - Vector databases and vector search technologies. - Agentic AI frameworks and multi-agent workflows. - Commercial large language models, preferably GPT-based solutions. - Experience with prompt engineering, structured outputs, m…