GenAI Developer – Hybrid (Toronto)

About the role

We are seeking a seasoned GenAI/LLM Engineer to join a leading Canadian bank on a long‑term, hybrid basis. You will design and deliver production‑grade AI solutions that augment traditional banking applications, working closely with both data and software engineering teams.

Key responsibilities

• Architect and implement practical, production‑ready GenAI solutions rather than proof‑of‑concept prototypes.
• Integrate LLM capabilities as an intelligent augmentation layer alongside Python‑based business logic, rules, and data pipelines.
• Build and maintain data pipelines, APIs, and backend services that support AI‑enhanced features.
• Design hybrid architectures that combine rule‑based systems with AI models, including embeddings, vector search, and prompt engineering.
• Deploy, monitor, and scale solutions on AWS cloud environments.

Required profile

• Proven experience as a GenAI/LLM specialist delivering production‑grade applications.
• Strong Python engineering background, especially in data processing and API development.
• Hands‑on experience with LLM frameworks and hybrid AI architectures.
• Deep understanding of embeddings, vector search, and prompt engineering techniques.
• Familiarity with cloud platforms (AWS preferred) and production deployment best practices.
• Clear awareness of AI model limitations and responsible AI principles.

Required skills

• Python
• LLM frameworks (e.g., LangChain, HuggingFace)
• Embeddings & vector search
• Prompt engineering
• AWS cloud services
• API development
• Data pipeline construction