Job Description

Job Title: AI/LLM Engineer

Location: Montreal, QC (Hybrid – 3 Days Onsite)
Duration: 12 Months

Required Skills

• Strong proficiency in Python (including async programming). 
• Experience building AI Agents using LangChain, LangGraph, or similar frameworks. 
• Strong understanding of LLMs, Prompt Engineering, RAG, ReAct, Tool Calling, Function Calling, and AI Workflow Orchestration. 
• Experience implementing MCP (Model Context Protocol), Memory, Context Management, and Tool Integration. 
• Experience developing REST APIs, Microservices, and scalable backend services. 
• Knowledge of Guardrails, Responsible AI, AI Safety, and LLM evaluation. 
• Experience with Snowflake, Databricks, and Lakehouse architectures. 
• Strong understanding of scalable cloud-based AI architectures. 
• Excellent analytical, problem-solving, and communication skills. 

Preferred Skills

• Experience with Vector Databases (Pinecone, ChromaDB, FAISS, Weaviate). 
• Experience with AWS, Azure, or Google Cloud. 
• Knowledge of Docker, Kubernetes, CI/CD, and MLOps. 
• Experience with enterprise AI deployments and RAG architectures. 

Key Responsibilities

• Design and develop autonomous AI agent systems using LangChain, LangGraph, and similar frameworks. 
• Build intelligent reasoning systems leveraging ReAct, tool calling, memory, and orchestration patterns. 
• Develop scalable Python applications, APIs, and microservices for AI solutions. 
• Implement guardrails and safety mechanisms for responsible AI systems. 
• Integrate AI applications with enterprise data platforms including Snowflake, Databricks, and Lakehouse. 
• Optimize LLM performance through prompt engineering, context management, and workflow automation. 
• Collaborate with cross-functional teams to deliver production-ready AI solutions