Senior AI Engineer, Agentic AI
Thomson Reuters4 days ago
Toronto, CanadaSenior
Responsibilities
- Design, develop, and deploy production LLM agents with multi-step workflows, RAG, prompt design, tool and function calling, and structured-output validation.
- Build specialist agents that integrate enterprise data, extract actionable signals, recommend next steps, and support human-in-the-loop review.
- Build and operate agent evaluation and observability systems, including guardrails, automated evaluations, drift detection, and production monitoring.
- Integrate agents with AWS infrastructure, enterprise APIs, and approved MCP servers.
- Develop reusable agent patterns and shared context, guardrail, and evaluation components.
- Create design documentation, architecture decision records, and system models.
- Collaborate with platform, data integration, governance, and product teams to turn business requirements into technical designs.
- Provide technical guidance, conduct code and design reviews, and mentor engineers.
Requirements
- At least 2 years of experience delivering practical applied AI or machine learning solutions.
- Hands-on experience building production LLM applications using RAG, prompt engineering, and tool or function calling.
- Experience building agent workflows with guardrails, evaluation, and reliability considerations.
- Strong Python programming skills and experience writing modular, well-tested, production-grade code.
- Experience with AWS services, networking, and security principles.
- Experience deploying services with Docker, CI/CD pipelines, and infrastructure as code.
- SQL and data integration experience, including cloud data warehouses and enterprise APIs.
- Working understanding of the machine learning lifecycle, including feature engineering, training, evaluation, and monitoring.
- Experience leading or supporting engineers through code and design reviews.
- Preferred experience with LangGraph, Strands, LangChain, CrewAI, multi-agent systems, MCP servers, vector stores, embeddings, retrieval pipelines, responsible AI, Python ML libraries, data validation frameworks, and AI coding assistants.
Benefits
- Flexible hybrid work model for office-based roles.
- Work-from-anywhere flexibility for up to 8 weeks per year and supportive work-life balance policies.
- Career development, continuous learning, and skills-development programs.
- Comprehensive benefits including flexible vacation, two company-wide Mental Health Days, Headspace access, retirement savings, tuition reimbursement, incentive programs, and wellbeing resources.
- Two paid volunteer days annually and opportunities for pro-bono consulting and ESG initiatives.
Categories
About Thomson Reuters
Thomson Reuters builds research platforms, workflow software, and data services for legal, tax and accounting, compliance, and government professionals, and operates the Reuters global news service. Flagship products include Westlaw for legal research and ONESOURCE and Checkpoint for tax and accounting, sold primarily via subscriptions and enterprise licenses. A public company headquartered in Toronto, it was formed in 2008 by combining Thomson Corporation and Reuters Group and is listed on the TSX and Nasdaq as TRI.