LLM Solutions Developer

We are looking for LLM Solutions Developer for a contract to Hire role in Mississauga. Would you be interested in this opportunity? This is a 3 days hybrid role in Mississauga. Its mandatory if you clear Karat test. We are looking for a talented and forward-thinking LLM Solutions Developer to join our AI Engineering team. In this role, you will design, build, and deploy production-grade solutions powered by Large Language Models (LLMs). You will work at the intersection of cutting-edge AI research and real-world software engineering, delivering intelligent, reliable, and scalable agentic systems. Key Responsibilities Design & Develop LLM-Based Solutions: Architect and implement end-to-end applications leveraging LLMs (e.g., GPT-4, Claude, Gemini, Llama) for tasks such as reasoning, summarization, code generation, and decision support. Agentic AI Systems: Build autonomous and semi-autonomous AI agents capable of multi-step reasoning, tool use, and goal-directed behavior using frameworks such as LangGraph, AutoGen, CrewAI, or custom implementations. Orchestration: Design and manage complex LLM orchestration pipelines, including multi-agent workflows, task routing, memory management, and context handling. Model Context Protocol (MCP): Implement and integrate MCP-compliant architectures to enable structured, context-aware communication between models, tools, and external systems. Guardrails & Safety: Integrate guardrail frameworks (e.g., NeMo Guardrails, Guardrails AI, custom rule engines) to enforce output safety, factual accuracy, policy compliance, and ethical AI standards. API Development & Integration: Design and expose RESTful or gRPC APIs for LLM-powered services; integrate with third-party APIs, enterprise systems, and data sources. Tool & Plugin Development: Build custom tools, plugins, and function-calling integrations that extend LLM capabilities (e.g., web search, database queries, code execution, document retrieval). RAG Pipelines: Develop Retrieval-Augmented Generation (RAG) systems using vector databases (e.g., Pinecone, Weaviate, pgvector) and embedding models. Evaluation & Observability: Implement LLM evaluation frameworks, tracing (e.g., LangSmith, OpenTelemetry), and monitoring dashboards to ensure quality, performance, and reliability. Collaboration: Work closely with product managers, data scientists, and platform engineers to translate business requirements into robust AI solutions. Documentation: Produce clear technical documentation, architecture diagrams, and runbooks for all developed systems. Required Skills & Experience Core LLM & AI Hands-on experience building and deploying LLM-based applications in production environments Deep understanding of prompt engineering, few-shot learning, chain-of-thought, and instruction tuning Experience with agentic AI frameworks (LangChain, LangGraph, AutoGen, CrewAI, Semantic Kernel, or similar) Familiarity with Model Context Protocol (MCP) and context window management strategies Experience implementing guardrails for LLM outputs (content filtering, hallucination mitigation, policy enforcement) Knowledge of RAG architectures, vector search, and embedding pipelines Orchestration & Infrastructure Experience designing multi-agent orchestration workflows and task delegation patterns Proficiency with API design and development (REST, GraphQL, or gRPC) Familiarity with tool/function calling patterns in LLM APIs (OpenAI function calling, Anthropic tool use, etc.) Experience with cloud platforms (AWS, GCP, or Azure) and containerization (Docker, Kubernetes) Software Engineering Strong proficiency in Python (primary); familiarity with TypeScript/JavaScript is a plus Experience with asynchronous programming, microservices, and event-driven architectures Solid understanding of software design patterns, clean code principles, and test-driven development Version control with Git and CI/CD pipeline experience

Design and deploy production-grade LLM solutions and autonomous agentic systems for reasoning and decision support. Implement orchestration pipelines, RAG systems, and safety guardrails to ensure reliable AI performance.

Requires strong proficiency in Python and hands-on experience building LLM applications using frameworks like LangChain or AutoGen. Candidates must be skilled in API development, vector search, and cloud infrastructure, and must pass a Karat test.

• TypeScriptPreferred

Identified from the job description. Confirm important requirements above.

• LLM Development
• Agentic AI
• LangGraph
• RAG Pipelines
• Python
• Prompt Engineering
• Vector Databases
• API Design
• Model Context Protocol
• Guardrails AI
• Docker
• Kubernetes
• TypeScript
• CI/CD
• Microservices
• Git

• Software
• Technology
• Engineering
• Data & Analytics
• Consulting

Minimum experience

5+ years

Apply by

Aug 30, 2026

Posting language

English

Working hours

40 hours per week

Office presence

3 days per week

Seniority

Mid-Senior level

Application method

Direct apply is available