VToronto, ONAI Engineer, LLM and RAG
Context
A contract role in Toronto, with three days per week onsite. The team works on LLM and retrieval-augmented generation solutions running on AWS cloud infrastructure.
What you'll do
- Design and build LLM and RAG-based AI applications
- Integrate MCP-based components into AI solutions
- Deploy and serve machine learning models on AWS, including SageMaker
- Build serverless and data pipelines using Lambda, S3, DynamoDB, Redshift and Step Functions
- Manage infrastructure as code with Terraform or CloudFormation
Profile
- Minimum 10 years of professional experience, mandatory
- Strong Python skills
- Hands-on experience with AI, ML and LLM projects
- Experience with AWS services such as ECS, EKS, Lambda and SageMaker
- Must have led at least one data science project