Opens LinkedIn
- Employment type
- Contract
- Experience level
- Senior
- Posting language
- English
- Office presence
- 1 days per week
- Application method
- Apply on LinkedIn (LinkedIn sign-in required)
Job summary
Design, build, and deploy production-grade generative AI and LLM applications, including agentic workflows and optimized RAG pipelines. Develop maintainable Python services, integrate systems through APIs, and implement evaluation, observability, containerization, and deployment practices while collaborating across engineering, data science, and product teams.
Job details
Senior AI Engineer – Generative AI & Agentic Systems Location: Toronto, ON – Hybrid, 1 day onsite per week Contract: 6 months with a high likelihood of extension Rate: Up to $100/hour incorporated The Opportunity We’re looking for a Senior AI Engineer to join a team building production-grade Generative AI and agentic applications. This is a hands-on engineering role focused on taking AI solutions beyond the proof-of-concept stage and building reliable systems that can operate in production at scale. You’ll work across Python development, LLM applications, agentic workflows, RAG, APIs, evaluation and deployment. The ideal candidate brings a strong software engineering foundation alongside hands-on experience building modern LLM and AI applications. What You’ll Be Doing Design, build and deploy production-grade Generative AI and LLM applications Develop agentic AI workflows and multi-step AI systems using tools such as LangGraph and LangChain Build and optimize Retrieval-Augmented Generation (RAG) pipelines Develop high-quality, maintainable Python services and applications Integrate LLM applications with internal and external systems through REST APIs Implement prompt engineering, structured outputs and tool/function calling Build evaluation and observability into AI applications to monitor quality, reliability, latency and model behaviour Work with Langfuse or comparable LLM observability/evaluation tooling Containerize and deploy applications using Docker and CI/CD pipelines Collaborate with engineering, data science and product teams to take AI solutions from design through production Contribute to technical standards and best practices for building reliable, scalable AI applications What We’re Looking For 7+ years of overall software, ML or AI engineering experience preferred Strong hands-on Python development experience with a focus on production-quality code Proven experience building and deploying production-grade systems, not just prototypes or proof-of-concepts Hands-on experience building LLM-based applications and agentic AI workflows Experience with LangGraph and/or LangChain Strong understanding of RAG, embeddings, vector search and retrieval techniques Experience with prompt engineering and structured outputs Experience integrating applications through REST APIs Familiarity with LLM evaluation and observability, ideally Langfuse or similar tooling Experience with Docker and CI/CD Solid understanding of machine learning and data science fundamentals Cloud Experience Experience with Google Cloud Platform (GCP) is preferred, particularly for candidates who have deployed AI/ML workloads in production. Strong experience with AWS or Azure is also considered. Nice to Have Multi-agent system development FastAPI MCP / tool-calling integrations LLM evaluation frameworks Vector databases and semantic search Kubernetes MLOps / LLMOps Production monitoring and model/application observability Experience working with large-scale enterprise applications This posting is for an existing vacancy with the organization. AI may be used to screen, assess or select applicants for the position.
What you’ll do
Design, build, and deploy production-grade generative AI and LLM applications, including agentic workflows and optimized RAG pipelines. Develop maintainable Python services, integrate systems through APIs, and implement evaluation, observability, containerization, and deployment practices while collaborating across engineering, data science, and product teams.
Requirements
Candidates should have 7+ years of software, ML, or AI engineering experience, strong production-quality Python skills, and hands-on experience deploying LLM applications and agentic workflows. They should understand RAG, embeddings, vector search, prompt engineering, APIs, evaluation and observability, Docker, and CI/CD; GCP experience is preferred, with AWS or Azure also considered.
Listed skills
- Python · Preferred
- prompt engineering · Preferred
- REST APIs · Preferred
- Docker · Preferred
- CI/CD · Preferred
Other relevant skills
Identified from the job description. Confirm important requirements above.
- Python
- Generative AI
- Large Language Models
- Agentic AI Workflows
- LangGraph
- LangChain
- Retrieval-Augmented Generation
- Embeddings
- Vector Search
- Prompt Engineering
- REST APIs
- LLM Evaluation
- LLM Observability
- Docker
- CI/CD
- Google Cloud Platform
Job areas
- Technology
- Software
- Data & Analytics
- Engineering
More jobs from Hays
Senior Accountant
- On-site
- Vancouver, BC
- Posted Nov 19, 2026
Tax Analyst
- On-site
- Burnaby, BC
- Posted Nov 19, 2026
Chargé de projet - Ebénisterie
- On-site
- Terrebonne, QC
- Posted Nov 19, 2026
Leasing Agent
- On-site
- Toronto, ON
- Posted Nov 19, 2026
