Skip to content
mimi

Lead Generative AI Engineer

Vancity

Vancouver · Hybrid Full-time Lead CA$125k – CA$154k/yr 3w ago

About the role

Our Story & Purpose

We’re Vancity, a member‑owned credit union built on the principles of inclusion and social justice. Since 1946, our relentless commitment to these values has helped us challenge the status quo and break down barriers. We’ve made bold commitments to become net‑zero by 2040 across all mortgages and loans, and we’re actively pursuing strategies in Indigenous banking and financial resilience for our members. As the largest private‑sector Living Wage Employer in Canada, we’re proud to be consistently recognized as one of the country’s Top Employers. If you’re ready to join our team of 2,300 diverse individuals, access competitive rewards and benefits, and be part of a greater movement – apply today!

Your Role in Supporting Our Members

We are seeking a Lead Gen AI Engineer to join our GenAI & Cognitive AI Pod, focused on building production‑ready Generative AI & Agentic AI solutions that support cognitive reasoning, automation, and decisioning. This role is highly hands‑on and best suited for a software engineer who understands AI deeply enough to build, deploy, and operate GenAI systems at scale. You will work closely with GenAI leadership, AI engineers, ML engineers, and RPA teams to design and deliver LLM‑based workflows, agentic pipelines, and GenAI APIs. This is a highly hands‑on engineering role; success is measured by production‑ready GenAI systems, not slideware or experimentation alone.

  • Full‑time, Permanent role based at our Head Office, in Vancouver, British Columbia
  • Reporting to Director of Artificial Intelligence (AI) Centre of Excellence
  • Open to candidates in BC and Ontario (hybrid work arrangement; on‑site for events and business demands when needed)

How You’ll Make an Impact

Build & Deliver GenAI Solutions

  • Build end‑to‑end LLM workflows, from data ingestion and retrieval through inference and response orchestration
  • Design and implement agentic AI pipelines that support decisioning, verification, and cognitive automation
  • Develop GenAI use cases including:
    • Documenting intelligence and verification
    • Communication mining and NLP
    • Knowledge retrieval and reasoning (RAG)
    • Agent‑based decision orchestration
  • Tune and optimize LLM usage (prompting strategies, embeddings, retrieval quality, latency, and cost)

RAG, NLP & Classic ML Techniques

  • Design and implement Retrieval‑Augmented Generation (RAG) pipelines, including indexing, chunking, embeddings, and retrieval strategies
  • Apply classic ML and NLP techniques where appropriate to improve accuracy, classification, extraction, or ranking
  • Collaborate with Data Science and ML Engineering partners to integrate predictive models into GenAI workflows

Cloud, Pipelines & Deployment

  • Build and deploy GenAI solutions on cloud (i.e., Azure and Databricks), following cloud‑native best practices
  • Implement API services to expose GenAI capabilities for downstream consumers (including RPA and business applications)
  • Contribute to CI/CD and deployment pipelines for GenAI workloads, including environment management and release practices
  • Partner with platform and cloud teams to ensure solutions are scalable, secure, and production‑ready

Integration & Collaboration

  • Integrate GenAI services with RPA workflows (UiPath) and existing ML pipelines
  • Work closely with:
    • GenAI & Agentic AI Lead
    • AI Engineers and Full‑Stack AI Developers
    • Cognitive UX / Prompt Engineers
  • Participate in agile delivery rituals (stand‑ups, planning, demos) and contribute to shared engineering standards

What You’ll Bring to the Team

  • 4–7 years of experience in software engineering, AI engineering, or ML‑adjacent engineering roles
  • Bachelor’s or Master’s degree in Computer Science, Software Engineering, or a related field
  • Strong hands‑on experience building and deploying cloud‑based services, with fluency in cloud (preferably Azure)
  • Practical experience working with Generative AI and LLM concepts, including RAG and agentic workflows
  • Proven ability to take solutions from prototype to production
  • Excellent Python and SQL skills (production‑quality code, data pipelines, APIs)
  • Strong understanding of:
    • LLM workflows and orchestration
    • Prompt engineering and retrieval strategies
    • API design and service integration
    • CI/CD concepts and cloud deployment patterns
  • Experience with agent frameworks or tool‑calling architectures

Extra Skills That Set You Apart

  • Experience with Azure AI services (e.g., Azure OpenAI, Azure ML concepts)
  • Experience with Databricks for data processing, ML, or GenAI workflows
  • Familiarity with document intelligence, OCR, NLP, or communication mining
  • Exposure to MLOps / GenAIOps concepts (model lifecycle, monitoring, evaluation)
  • Experience integrating AI services into RPA or automation platforms (i.e., UiPath, Power Automate)
  • Familiarity with other cloud ecosystems (AWS or GCP)

You’ll Thrive Here If You Are

  • A Hands‑on Automation Builder: You enjoy writing, testing, and deploying automations that work reliably in real production environments.
  • Technically Curious: You’re interested in how RPA can be enhanced with AI, agentic workflows, and cloud services to solve more complex problems.
  • Collaborative: You work well with architects, AI engineers, and business partners, and you value shared standards and reusable solutions.
  • Quality Driven: You care about robustness, error handling, and maintainability, not just getting something to work once.

We value lived experience, so if you are interested in this role, we encourage you to apply even if you feel your skills don’t perfectly align with those listed.

What You’ll Earn

  • Salary range: $125,000 – $154,350 per annum (base pay may vary based on qualifications, skills, experience, and internal equity)
  • Eligibility for our annual incentive program (subject to program eligibility requirements)

Open until Filled

Why You’ll Love Working Here

  • Living Wage Employer: We’re the largest private‑sector Living Wage Employer in Canada and consistently ranked among Canada’s Top Employers.
  • Customizable Benefits: Permanent employees receive flexible benefit packages that can be tailored annually to meet evolving needs.
  • Generous Vacation: New employees start with 3–4 weeks of vacation per year, with additional days earned overtime.
  • Extra Stat Holidays: In addition to BC’s 11 statutory holidays, we offer 2 extra days, plus care days for personal or family illness.
  • Immediate Health Coverage: Health and dental benefits begin on your hire date, with three levels of coverage to choose from.
  • Defined Benefit Pension: Our retirement plan provides a guaranteed income for life, recognizing that retirement looks different for everyone.

Vancity Talent Programs

Vancity supports an inclusive hiring process for candidates who self‑identify as Indigenous, Black, or Trans. With special permission from the BC Human Rights Commissioner, this initiative provides access to career development opportunities, prioritized job screening, and feedback. Any information you choose to share will be stored securely and used only for recruitment and career development connected to this initiative, in line with the BC Personal Information Protection Act (PIPA). For details, please see our dedicated Talent Programs job posting.

Accessibility & Accommodations

At Vancity we’re committed to creating a welcoming and inclusive workplace to help our people and communities thrive and prosper. Diversity in our workforce is integral so that we can truly represent, understand, and respond to our community needs and deliver our member experience. This role is an open vacancy, and our hiring process is grounded in fairness, transparency, and inclusion. We are committed to an inclusive, barrier‑free, and accessible recruitment experience for all candidates.

If you require any accommodations or support at any stage of the recruitment process (including the application stage), please contact our Talent Acquisition team at recruitment@vancity.com. We’ll work with you to ensure your needs are met promptly and effectively. All requests will be handled with the utmost respect and confidentiality, so you can participate fully in the process

Requirements

  • 4-7 years of experience in software engineering, AI engineering, or ML adjacent engineering roles
  • Bachelor's or Master's degree in Computer Science, Software Engineering, or a related field.
  • Strong hands on experience building and deploying cloud based services, with fluency in cloud (preferably Azure)
  • Practical experience working with Generative AI and LLM concepts, including RAG and agentic workflows
  • Proven ability to take solutions from prototype to production
  • Excellent Python and SQL skills (production quality code, data pipelines, APIs)
  • Strong understanding of: LLM workflows and orchestration
  • Prompt engineering and retrieval strategies
  • API design and service integration
  • CI/CD concepts and cloud deployment patterns
  • Experience with agent frameworks or tool calling architectures

Responsibilities

  • Build & Deliver GenAI Solutions
  • Building end to end LLM workflows, from data ingestion and retrieval through inference and response orchestration
  • Designing and implementing agentic AI pipelines that support decisioning, verification, and cognitive automation
  • Developing GenAI use cases including: - Documenting intelligence and verification - Communication mining and NLP - Knowledge retrieval and reasoning (RAG) - Agent based decision orchestration
  • Tune and optimize LLM usage (prompting strategies, embeddings, retrieval quality, latency, and cost)
  • RAG, NLP & Classic ML Techniques
  • Design and implement Retrieval Augmented Generation (RAG) pipelines, including indexing, chunking, embeddings, and retrieval strategies
  • Apply classic ML and NLP techniques where appropriate to improve accuracy, classification, extraction, or ranking
  • Collaborate with Data Science and ML Engineering partners to integrate predictive models into GenAI workflows
  • Cloud, Pipelines & Deployment
  • Build and deploy GenAI solutions on cloud (i.e. Azure and Databricks), following cloud native best practices
  • Implement API services to expose GenAI capabilities for downstream consumers (including RPA and business applications)
  • Contribute to CI/CD and deployment pipelines for GenAI workloads, including environment management and release practices
  • Partner with platform and cloud teams to ensure solutions are scalable, secure, and production ready
  • Integration & Collaboration
  • Integrate GenAI services with RPA workflows (UiPath) and existing ML pipelines
  • Work closely with: - GenAI & Agentic AI Lead - AI Engineers and Full Stack AI Developers - Cognitive UX / Prompt Engineers
  • Participating in agile delivery rituals (stand-ups, planning, demos) and contribute to shared engineering standards

Benefits

health insurancedental insurancevision insurancevacationstat holidayscare daysDefined Benefit Pension

Skills

Azure AIAzure DatabricksAzure MLAzure OpenAIDatabricksDockerGCPLLMMLOpsNLPPower AutomatePythonRAGSQLUiPath

Don't send a generic resume

Paste this job description into Mimi and get a resume tailored to exactly what the hiring team is looking for.

Get started free