LLM / Generative AI Platform Engineer
Overview
Stathletes is revolutionizing professional hockey data and analytics for the world’s premier leagues, teams, players, agents, media, sportsbooks and digital platforms. Our mission is to offer the most comprehensive dataset in sports to drive the most accurate and insightful statistical analysis available in the market.
And we’re looking for an experienced LLM / Generative AI Platform Engineer to join our team! As a key member, you will take ownership of building and scaling conversational AI capabilities across our software suite—delivering dynamic, data-driven answers powered by Stathletes’ proprietary data and workflows.
The Role
As an LLM / Generative AI Platform Engineer, you’ll lead the development of production-grade conversational systems: from prompt + evaluation pipelines, to retrieval and tool-calling, to integrations with LLM providers (e.g., ChatGPT/OpenAI and Google Gemini). Working closely with our team of engineers, you’ll have significant influence over our architecture and AI stack as we scale to deliver cutting-edge features and insights.
You will build systems that can:
- Answer complex questions with grounded, verifiable outputs
- Retrieve real-time or frequently changing data via tools/APIs/SQL
- Use RAG and/or tool-calling to support accurate, data-driven responses
- Operate reliably under production constraints (latency, cost, privacy, uptime)
What We Care About
- Allowing you to do your best work. We’re async-first with Slack and keep meetings to a minimum to protect heads-down time.
- Productivity. We ruthlessly evaluate requests and opportunities to pursue and ship only meaningful improvements to the business.
- Ownership of product, code and process. We hire first liners and let them make decisions independently.
- Doing a lot with a little. Simple, creative, effective and stable solves through small teams.
What you’ll work on
- LLM application architecture: conversation state, memory, tool routing, function calling, multi-step workflows, guardrails
- Integrations: OpenAI / Gemini (and similar) APIs, streaming responses, structured outputs, auth + secrets handling
- Prompt engineering at scale: prompt templates, prompt/version management, structured prompting patterns, safety + refusal handling
- Retrieval & grounding: embeddings, chunking strategies, metadata, hybrid retrieval, reranking, citations/traceability, vector DBs
- Tooling for dynamic answers: SQL/tool execution, API connectors, realtime/freshness strategies, caching, fallbacks, rate-limit design
- Evaluation & monitoring: offline eval sets, LLM-as-judge (where appropriate), regression tests, quality dashboards, observability
- Performance & reliability: latency optimization, token/cost management, response consistency, error handling, incident-ready design
Possibly later (growth path): Help guide selection, hosting strategy, and fine-tuning of open-source LLMs (e.g., Mistral and similar), including data curation, evals, and deployment patterns.
About You
We would love to hear from you if you have:
- Experience building and shipping LLM-powered applications to production
- Strong Python (and/or TypeScript) skills and comfort working across APIs/services
- Hands-on experience with RAG, vector databases, embeddings, and retrieval evaluation
- Experience implementing tool-calling / function calling and integrating structured data sources (SQL/APIs)
- Familiarity with modern LLM frameworks (e.g., LangChain/LangGraph, LlamaIndex, or equivalent patterns)
- A solid foundation in software engineering: system design, data structures, testing, and maintainable architecture
- Strong collaboration skills—able to translate product needs into robust technical solutions
Nice-to-haves:
- Experience with event-driven systems, queues, background jobs, and data pipelines
- Familiarity with privacy/security best practices for handling customer or sensitive data
- Interest in sports analytics, computer vision, or applied ML
- A love of hockey, and/or a passion for delivering data products
What we offer
- Your choice: work fully remotely, or from our offices in downtown St. Catharines
- A comprehensive and competitive health and dental benefit plan for you and your family
- A budget for setting up your home office
- An inviting and dynamic team environment
- A supportive environment for career development and educational enrichment
- A culture that values innovation, with opportunities for internal growth and development
Applying
We know applying for a job can be emotionally draining, and waiting weeks without hearing back is incredibly frustrating. We pledge to respond to every application, and we commit to being open and transparent throughout the application process. If you have any questions, or if you require special accommodation please let us know at careers@stathletes.com.
We are committed to fostering a diverse, inclusive workplace and are an equal opportunity employer. All qualified applicants will receive consideration for employment without regard to any protected characteristics.
This role is open to Canadian citizens, permanent residents, and other individuals legally authorized to work in Canada.
One final note: don’t be discouraged if you don’t meet every single qualification—we encourage you to apply even if you’re not a 100% perfect match.
If joining our team feels like the perfect next step in your career, apply today with your resume. Come help us elevate the game you love!
Apply Now
Smarter, data-driven strategies that elevate hockey performance.
We proudly provide exclusive data, reports, insights, and visualizations to major North American hockey leagues, partners, and affiliates
Follow Stathletes
St Catharines, Toronto & Waterloo
Follow Stathletes
All Rights Reserved.
St Catharines, Toronto & Waterloo
Any third party images, logos, trademarks or copyrights are the property of their respective owners.



