AI Platform Engineer
- Toronto, ON, Canada
Contract
Applications open in a new tab.
Job details
- Job type
- Contract
- Apply by
- Posting language
- English
- Posted
Original job description
AI Platform Engineer - Long-term Contract | Hybrid, Toronto/GTA | Insurance Client
We are hiring an AI Platform Engineer for a long-term contract with a leading insurance client. Hybrid model - 2 days per week onsite in the GTA. Competitive hourly rate.
What you'll work on:
Agentic AI & Agent Frameworks: Developing and coordinating specialized domain agents using frameworks like LangChain, LangGraph, Google ADK, or similar - multi-agent orchestration, agent gateway architectures, and MCP server connectivity.
LLM Engineering: Building production systems on large language models - prompt engineering, fine-tuning, evaluation, and LLMOps.
Generative AI & Data Retrieval: Building Generative AI and Retrieval-Augmented Generation (RAG) integrations - vector databases, embeddings, and connecting agents with internal datastores and unstructured knowledge bases.
Internal Platform & API Engineering: Moving from traditional application builds to scalable internal AI platforms - API development (e.g., FastAPI), workflow orchestration, and robust tool-invocation frameworks.
Governance & Observability: Implementing governance frameworks via specialized compliance agents (e.g., validating rule-based eligibility), guardrails, monitoring, audit trails, and evaluation from day one.
The details:
- Location: Toronto, ON - Hybrid (2 days/week onsite)
- Contract: Long-term
- Client: Leading insurance company
- Rate: Competitive hourly rate, based on experience
- Cloud: Cloud-agnostic - GCP, AWS, or Azure experience welcome
Interested? Apply here or reach out directly - we'd love to hear from you. 📩 info@genaiconsulting.ca
#AIJobs #AIPlatformEngineer #AgenticAI #RAG #LLM #MCP #LangChain #Hiring #TorontoJobs #HybridJobs
More about this job
Responsibilities
Develop and coordinate specialized AI agents, multi-agent orchestration, and MCP connectivity, while building production LLM and RAG systems integrated with internal data sources. Develop scalable internal AI platforms and APIs, and implement governance, guardrails, monitoring, audit trails, and evaluation.
Requirements
The role calls for experience with agent frameworks such as LangChain, LangGraph, or Google ADK, as well as production LLM engineering, RAG, vector databases, and embeddings. It also involves API development, workflow orchestration, governance, and observability; experience with GCP, AWS, or Azure is welcome.
Skills
- Agentic AI
- LangChain
- LangGraph
- Google ADK
- Multi-Agent Orchestration
- MCP
- LLM Engineering
- Prompt Engineering
- Fine-Tuning
- LLMOps
- Generative AI
- Retrieval-Augmented Generation
- Vector Databases
- Embeddings
- FastAPI
- Workflow Orchestration
Visa sponsorship
Not detected in the job text
Categories
- Technology
- Software
- Engineering
- Data & Analytics
Keywords
- Agentic AI
- LangChain
- LangGraph
- Google ADK
- Multi-Agent Orchestration
- Agent Gateway Architecture
- MCP Server Connectivity
- Large Language Models
- Prompt Engineering
- Fine-Tuning
- LLM Evaluation
- LLMOps
- Generative AI
- Retrieval-Augmented Generation
- Vector Databases
- Embeddings
- Internal Datastores
- Unstructured Knowledge Bases
- API Development
- FastAPI
- Workflow Orchestration
- Tool Invocation Frameworks
- AI Governance
- Compliance Agents
- Guardrails
- Monitoring
- Audit Trails
- GCP
- AWS
- Azure