19 Nov
|
Peltrex
|
Toronto
Architect RAG pipelines and production AI systems as an AI and LLM Engineer in Toronto, working hybrid for enterprise clients. Apply Python and cloud deployment expertise across complex delivery work.
This full-time AI and LLM Engineer role supports an AI practice serving financial services, healthcare, and retail clients. You will work across the AI engineering stack, from data ingestion through deployment. The position emphasizes foundation model selection, observability, prompt engineering, and evaluation.
Key Responsibilities:
- Design and deliver production-grade AI systems
- Architect retrieval-augmented generation pipelines
- Evaluate and select foundation models
- Build observability tooling for AI workloads
- Work across data ingestion through deployment
Requirements:
- Three-plus years of software engineering experience
- At least one year focused on LLM or ML systems
- Proficiency in Python and familiarity with LLM SDKs
- Experience deploying AI workloads in cloud environments
- Solid grasp of prompt engineering and evaluation frameworks
Bring Python, cloud deployment, RAG, and evaluation expertise to production AI engineering for enterprise clients in Toronto.
#J-18808-Ljbffr
📌 AI LLM Engineer Toronto Hybrid
🏢 Peltrex
📍 Toronto