AI Engineer

Charger Logistics Inc•Brampton, ON

2d•Onsite

About The Position

Charger Logistics Inc. is a world-class asset-based carrier with locations across North America. With over 20 years of experience providing the best logistics solutions, Charger logistics has transformed into a world-class transport provider and continue to grow. We are looking for a highly motivated AI Engineer to join our team based out of our Brampton office and contribute to the development of AI-driven solutions for various departments. This role focuses on building production AI agents and MCP (Model Context Protocol) integrations that automate real logistics workflows—dispatch, billing, compliance, and fleet operations—improving the reliability, transparency, and efficiency of AI applications in real-world, high-stakes environments.

Requirements

Bachelor's in Computer Science, Artificial Intelligence, or a related technical field.
Strong communication skills and experience working in interdisciplinary or team-based environments.
Solid understanding of REST APIs, microservices architecture, and AI/ML concepts.
Experience building production-grade AI applications in Python—not just notebooks or prototypes.
Hands-on proficiency with LLM integration: function calling, tool use, structured outputs (OpenAI, Anthropic, or Google APIs).
Solid understanding of knowledge retrieval patterns including RAG (Retrieval-Augmented Generation), with familiarity of emerging approaches like KAG (Knowledge-Augmented Generation) and CAG (Cache-Augmented Generation).
Proficiency with SQL and at least one analytical data platform (BigQuery, Snowflake, or similar).
Experience with cloud platforms and container orchestration (Kubernetes).

Nice To Haves

Background in MCP, agent orchestration frameworks, knowledge graphs, or streaming data systems is a strong asset.

Responsibilities

Design, develop, and deploy MCP servers exposing domain services as AI-consumable tools with proper authentication, observability, and error handling.
Build multi-agent workflows using orchestration frameworks and agent-to-agent communication protocols for complex logistics automation.
Develop and optimize knowledge retrieval pipelines using RAG, KAG, and CAG strategies—selecting the right approach based on query complexity, data volatility, and domain reasoning requirements.
Design hybrid retrieval architectures that route between CAG for static reference data, RAG for dynamic operational queries, and KAG for multi-hop reasoning across structured domain knowledge.
Implement LLM integration layers—prompt engineering, function calling, structured output parsing, and model routing for domain accuracy.
Collaborate with cross-functional teams to collect requirements and translate operational workflows into agent capabilities.
Deploy and maintain agent infrastructure on Kubernetes with GitOps practices and observability tooling.