TELUS Health is empowering every person to live their healthiest life. Guided by our vision, we are leveraging the power of our leading edge technology and focusing on the uniqueness of each individual to create the future of health. As a global-leading health and well-being provider – encompassing physical, mental and financial health – TELUS Health is improving health outcomes for consumers, patients, healthcare professionals, employers and employees.
We’re looking for a talented LLM/Generative-AI Developer to join the AVA Team.
Working in an Agile, multi-disciplinary team, you will design, build, and fine-tune generative-AI services that power personalized, conversational experiences for our members. You’ll partner closely with product managers, UX designers, data scientists, and backend engineers to ship AI-driven features that enhance member engagement, self-service, and satisfaction.
This is an applied engineering role focused on building production LLM applications - RAG pipelines, agentic and tool-using workflows, and inference services - rather than foundational model research.
You don’t need to match every requirement. If you’ve shipped real LLM features in production and are excited by this work, we’d like to hear from you!
What's In It For You:
- Competitive base salary plus performance bonus.
- Comprehensive health, dental, and vision benefits.
- Flexible hours and a flexible workstyle policy.
- The chance to shape AI-driven experiences for millions of AVA members across Canada.
What You'll Do:
LLM Engineering
- Design and integrate LLM services (Azure OpenAI, OpenAI, IBM Watson, etc.) for the AVA chatbot and feature releases.
- Apply prompt engineering, Retrieval-Augmented Generation (RAG), tool-use/agentic orchestration (function calling, structured outputs), and token-management best practices.
Evaluation & Quality
- Build evaluation harnesses for LLM outputs - curated eval sets, automated scoring, and regression checks - alongside unit and integration tests, so prompt and model changes ship safely.
Infrastructure & CI/CD
- Build and operate scalable inference pipelines (Docker, Kubernetes, Azure Functions). Automate CI/CD (Azure DevOps) for rapid, reliable deployment of model updates and new features.
Data Ingestion & RAG
- Ingest client data (PDF, Excel, CSV) into Azure AI Search/Pinecone; design index schemas, skillsets, and hybrid vector-keyword queries.
- Build frameworks for new client data, demographics, and expression rules.
- Document runbooks and validate datasets and access-control rules.
Observability & Monitoring
- Instrument tracing and monitoring (Langfuse, OpenTelemetry, Azure Monitor) for model performance, cost, and safety.
- Set up alerts for latency, error-rate, and token-usage spikes.
Safety, Compliance & Governance
- Implement content moderation, PII redaction, prompt-injection defences, bias mitigation, and company-specific privacy and security compliance.
- Produce audit logs and maintain documentation for regulatory reviews.
Collaboration & Mentoring
- Partner with UX to define conversational flows and UI components.
- Mentor peers on LLM best practices and contribute to internal knowledge bases and tech talks.
Continuous Improvement
- Run A/B testing and analytics to measure impact on member satisfaction and portal KPIs.
- Identify automation opportunities across the software-development lifecycle.
What You Bring:
- Bachelor’s/Master’s degree in Computer Science, AI, ML, or a related field - or equivalent professional experience.
- 5+ years in software or ML engineering, with 2+ years of hands-on experience building and shipping LLM/generative-AI applications in production.*
- Bilingual in both French and English, oral and written.
- Demonstrated depth of applied GenAI work (shipped RAG systems, chatbots, agents, or inference services).
- Strong hands-on experience with the core stack: Node.js/Express (REST APIs, async patterns); LLM/RAG (Azure OpenAI & OpenAI SDKs, prompt design, tool-use/function calling, token management); vector search (Azure AI Search or Pinecone); and LLM evaluation (eval sets, automated scoring, regression checks).
- Sound judgment on model selection across providers, balancing quality, latency, and cost.
- Working familiarity with several of the following (not all required): Python; agent frameworks (LangChain, LangGraph, Semantic Kernel); MongoDB/SQL Server; Azure platform (Blob Storage, Entra ID); observability (Langfuse, OpenTelemetry); data ingestion (PDF/Excel/CSV parsing, Azure Document Intelligence); Docker & Azure DevOps; Swagger/OpenAPI.
- Strong analytical mindset, clear communication, a collaborative attitude, and the ability to explain complex AI concepts to non-technical stakeholders.
- Familiarity with enterprise software architecture, Agile delivery, and chatbot products.
Assets:
- Experience with Octopus Deploy or similar deployment tools.
- Prior work on multimodal RAG pipelines (text + image).
- Exposure to MLOps (MLflow, DVC, Terraform).
- Knowledge of member-services or health-care portals.
*Note: Given the rapid emergence of Large Language Models, we prioritize demonstrated success in shipping GenAI products to production and strong software fundamentals over total years of experience in this specific domain.
Intermediate knowledge of English is required because you will on a regular basis interact in English with external parties (clients, suppliers, candidates, external partners, etc.); interact in English with internal parties (colleagues, internal partners, stakeholders, etc.); and work with IT tools whose interface is only accessible in English as part of this position's main responsibilities given its international scope.
A bit about us
We’re a people-focused, customer-first, purpose-driven team who works together every day to innovate and do good. We improve lives through our technology solutions and foster a culture of innovation that empowers team members to solve complex problems and create remarkable human outcomes in a digital world.
TELUS is proud to foster an inclusive culture that embraces diversity. We are committed to fair employment practices and all qualified applicants will receive consideration for employment. We offer accommodation for applicants with disabilities, as required, during the recruitment process.
Disclaimer: In accordance with the TELUS Health Solutions Data Center Security Policy, as a condition of employment, all team members whose job functions require they work at a Data Center and/or have access to detailed knowledge of technology related to client service delivery, are subject to a Personnel Security Screening conducted through the Government of Canada.
Note for Quebec candidates: if knowledge of English is required for this position, it is because the team member will be asked, on a regular basis, to interact in English with external or internal parties or to use English applications or software as part of their tasks.
By applying to this role, you understand and agree that your information will be shared with the TELUS Group of Companies’ Talent Acquisition team(s) and/or any leader(s) who will be part of the selection process.