Senior AI Engineer - Evisort AI

Workday•Vancouver, BC

1d•CA$169,000 - CA$253,000•Hybrid

About The Position

Join the Evisort AI team at Workday, which powers Document Intelligence AI and Workday's CLM and Contract Intelligence offerings. Our mission is to change the way business deals get done. We build ground breaking AI technology that can read and understand contract language to make every part of the deal-making process from drafting, negotiating, reviewing, approving, or managing the contracts happen faster, better, with reduced risks. We build AI first products, and automate manual work, freeing up our customers time and accelerating their businesses. You will be joining the Evisort AI team, which functions as a startup within Workday. This is your opportunity to build at the pace of innovation of a startup, while backed by the enormous support and impacting Workday's incredible customer base of 70M+ users. As an AI Engineer, you will help develop tailored user experiences using advanced LLMs, Knowledge Graphs, personalization, and predictive analysis. You will collaborate with other engineers to deliver AI solutions across Workday's product ecosystem and utilize software and data engineering stacks to enable training, deployment, and lifecycle management of various AI pipelines. You will develop and deploy new products at scale and leverage Workday's vast computing resources on rich datasets to deliver transformative value to our customers. In addition to contributing to feature and service development, you must have an approach of continuous improvement, passion for quality, scale, and security. You must be curious and prepared to question or challenge choices and practices where they don't make sense to you or could be improved. You also should have a product approach and strong intuition around how AI can drive a better customer experience. Lastly, a strong sense of ownership and teamwork are essential to succeed in this role.

Requirements

8+ years of professional experience in software engineering and product-building, with a proven track record of shipping and maintaining production code at scale.
3+ years of hands-on experience integrating large models (LLMs, Foundation Models) and modern AI APIs into user-facing enterprise products.
1–2+ years of hands-on experience building with modern AI orchestration frameworks (e.g., LangChain, LlamaIndex, or multi-agent frameworks) and implementing advanced prompt engineering techniques to manage complex agentic workflows.
4+ years of experience optimizing application performance, specifically tackling product constraints such as API latency, token management, and user interaction design.
4+ years of proven experience leveraging cloud computing platforms (e.g., AWS, GCP) to deploy highly responsive, scalable systems.
Hands-on experience deploying and operating services in containerized, cloud-native environments (Docker, Kubernetes), with exposure to infrastructure-as-code and GitOps tooling (e.g., Terraform, Helm, ArgoCD).

Nice To Haves

Bachelor’s degree (Master’s preferred) in Computer Science, Software Engineering, or equivalent technical field.
Product-First AI Mindset: Deep focus on business value, user experience, and applying deep learning or large models directly to solve practical end-user challenges.
System Design & Reusability: Proven ability to architect robust application layers that wrap around AI models, establishing reusable patterns for system predictability, error handling, and seamless UX integration.
Experimentation & Evaluation: Skilled in rapid prototyping, benchmarking model outputs against product requirements, and setting up automated evaluation metrics (e.g., assessing retrieval quality and agentic behavior).
Hands-on experience with production observability and monitoring tooling (e.g., Prometheus/Grafana, OpenTelemetry, Sentry, Datadog) to debug, trace, and measure live systems.
Experience using feature-flag/experimentation platforms (e.g., LaunchDarkly) to safely roll out, A/B test, and decommission changes, including flag lifecycle and cleanup discipline.
Familiarity with data persistence and async processing - relational databases and schema migrations (e.g., PostgreSQL), caching (e.g., Redis), and message/queue or task workflows (e.g., Celery, Kafka, SQS).
A track record of writing well-tested, maintainable production code with attention to code quality, security scanning, and dependency hygiene (e.g., unit/integration tests, SonarQube, dependency tooling).
Familiarity with full-stack development - building web UIs (e.g., React, TypeScript) and backend services/REST APIs in Python (e.g., FastAPI, Django).
Technical Leadership & Mentorship: Proven track record of technically leading engineering workstreams, taking ownership of the development lifecycle, and mentoring junior-to-mid level engineers.
Collaborative Communication: Excellent interpersonal skills, with a knack for bridging the gap between product management, design, and foundational ML infrastructure teams.
Thrives in Ambiguity: Highly autonomous builder capable of taking open-ended product goals and breaking them down into concrete, scalable engineering realities.

Responsibilities

Develop tailored user experiences using advanced LLMs, Knowledge Graphs, personalization, and predictive analysis.
Collaborate with other engineers to deliver AI solutions across Workday's product ecosystem.
Utilize software and data engineering stacks to enable training, deployment, and lifecycle management of various AI pipelines.
Develop and deploy new products at scale.
Leverage Workday's vast computing resources on rich datasets to deliver transformative value to our customers.
Contribute to feature and service development with an approach of continuous improvement, passion for quality, scale, and security.
Question or challenge choices and practices where they don't make sense or could be improved.
Apply a product approach and strong intuition around how AI can drive a better customer experience.
Demonstrate a strong sense of ownership and teamwork.