AI / Agent Engineer

Appnovation Technologies•Toronto, ON

10h

About The Position

Appnovation is a global, full-service digital partner that combines Strategy, Experience & Design, Engineering and Managed Services. We build digital solutions that deliver real impact today and serve as foundations for future growth. Bold ambition. Practical action. Endless possibilities. Technology is foundational to all of Appnovation’s offerings, from consulting to digital innovation, to digital product and service creation. The technology department is focused on delivering software solutions that enable rich consumer experiences, from mobile and web applications to advanced analytics and machine learning, to content and engagement management service enablement platforms. Inherent throughout our tech capabilities is deep expertise in the Software Development Life Cycle, a drive for creativity, a passion for the craft, and collaboration with other disciplines - all foundational ingredients in successful digital experiences and client partnerships. As an AI / Agent Engineer — an “AI Builder” — you will join a highly motivated and experienced team at the core of every pod, building and evolving the agentic layer of our platform. You will craft the MCP servers, tools, skills and graph-RAG pipelines that make documents intelligible to multiple large language models, and partner with product, data and QA to continuously raise answer quality and factual grounding. We are looking for people who bring a strong, solution-focused mindset, thrive amid fast-moving AI tooling, and get things done.

Requirements

Bachelor’s Degree in Computer Science, Engineering, or equivalent practical experience.
5+ years of experience in software engineering, with 2+ years in AI/ML or LLM-based applications.
Strong Python, with hands-on experience in LLM application development and agentic patterns.
Direct experience building MCP servers, tools, and skills.
Experience with RAG and graph-RAG systems, vector databases, and embeddings.
Familiarity with graph data stores (Neo4j and/or Postgres/Supabase-based graph implementations).
Comfortable working against multiple LLM providers (e.g., Claude, Gemini).
Solid software engineering fundamentals: version control (Git), testing, and CI/CD.
Strong problem-solving and communication skills, with the ability to work independently in ambiguity.

Nice To Haves

You think about how to scale, automate and operate, not just how to build a solution to an immediate problem
You understand lean thinking
You set high standards for code quality, performance/scalability and security and seek continuous improvement
You have solid analytical, problem solving and decision-making skills
You have customer first mindset and a devotion to customer service
You engage and build positive internal and external client relationships, while managing multiple initiatives, often with competing priorities
You have strong self-initiative, passion, interpersonal, oral and written communication and collaboration skills with the ability to work, influence and make an impact in a cross-functional environment with all levels of the organization
You are responsive and thrive in a fast-paced diverse high-performance environment with rapidly changing business needs
You actively seek out things outside your comfort zone with the ability to rapidly learn and take advantage of new concepts, business models, and technologies
You have prior experience in consulting
Prior experience and connections in the Life Sciences industry is preferred

Responsibilities

Build and evolve MCP servers, tools, and skills that expose the platform to multiple LLMs (e.g., Claude, Gemini).
Design and refine the graph-RAG pipeline that transforms documents into agent-friendly representations of facts, entities, and relationships.
Implement retrieval across multiple tiers (source document, vector-RAG, dense graph) and temporal replay.
Partner with QA on eval-driven improvements to answer quality and factual grounding.
Write clean, well-tested, production-grade code and participate in code reviews.
Collaborate closely with product, data, and QA in an agile/sprint model.
Document designs, prompts, and tool interfaces for maintainability and handover.
Monitor deployed agents/models, troubleshoot issues, and iterate on performance.
Stay current with the fast-moving LLM/agent tooling landscape.