Sr. LLM Engineer

About TELUS Digital

Welcome to TELUS Digital — where innovation drives impact at a global scale. As an award-winning digital product consultancy and the digital division of TELUS, one of Canada’s largest telecommunications providers, we design and deliver transformative customer experiences through cutting-edge technology, agile thinking, and a people-first culture.

With a global team across North America, South America, Central America, Europe, and APAC, we offer end-to-end expertise across eight core service areas: Digital Product Consulting, Digital Marketing Services, Data & AI, Strategy Consulting, Business Operations Modernization, Enterprise Applications, Cloud Engineering, and QA & Test Engineering.

From mobile apps and websites to voice UI, chatbots, AI, customer service, and in-store solutions, TELUS Digital enables seamless, trusted, and digitally powered experiences that meet customers wherever they are — all backed by the secure infrastructure and scale of our multi-billion-dollar parent company.

Location & Flexibility

• This role will be Work From Home (Canada)

The Opportunity

Sr. LLM Engineer with Telco_AI_Zuora and Revenue Reporting Experience

Key Skills: Development with python/Java using AI, sql databases and data analytics, preferably with Zuora and revenue reporting experience

We are seeking a skilled LLM Engineer to design, develop, fine-tune, and deploy Large Language Model (LLM)–based solutions. The ideal candidate will work closely with product managers, and software engineers to build scalable, secure, and high-performance AI applications powered by state-of-the-art language models.

Key Responsibilities

• Design, develop, and deploy applications using Large Language Models (LLMs) such as GPT, Claude, LLaMA, or similar
• Fine-tune, evaluate, and optimize LLMs for domain-specific use cases
• Implement prompt engineering, retrieval-augmented generation (RAG), and agent-based workflows
• Build scalable APIs and services to integrate LLMs into production systems
• Optimize model performance, latency, and cost
• Ensure responsible AI practices, including data privacy, bias mitigation, and security
• Collaborate with cross-functional teams to translate business requirements into AI solutions
• Monitor and improve model outputs through continuous evaluation and feedback loops
• Stay current with advancements in NLP, LLM frameworks, and AI research

Required Qualifications

• Strong programming skills in Python (required); experience with JavaScript or Java is a plus
• Hands-on experience with LLMs and NLP techniques
• Experience with frameworks such as LangChain, LlamaIndex, Hugging Face, OpenAI APIs, or similar
• Understanding of machine learning concepts, transformers, and deep learning
• Experience building and deploying cloud-based applications (AWS, Azure, or Google Cloud Platform)
• Familiarity with REST APIs, microservices, and containerization (Docker, Kubernetes)
• Experience with Vertex AI in GCP

Preferred Qualifications

• Experience with fine-tuning open-source LLMs
• Knowledge of vector databases (FAISS, Pinecone, Weaviate, Chroma, etc.)
• Experience with MLOps tools and CI/CD pipelines
• Exposure to reinforcement learning, evaluation metrics, or synthetic data generation
• Prior experience working on production AI systems