Software Engineer and Senior Software Engineer - AI Platform

Workday•Vancouver, BC

3d•Hybrid

About The Position

We are looking for Software Development Engineers to help build our Agent Platform—the infrastructure that enables teams to develop, deploy, and operate AI agents in production. In this role, you will design and implement backend services, systems, and tooling that support agent-based applications. You’ll work on problems spanning distributed systems, orchestration, and developer experience, helping teams reliably build and scale AI-powered workflows. This is a great opportunity for an engineer who enjoys building production systems, solving complex technical problems, and working at the intersection of backend engineering and AI.

Requirements

3+ years of software development experience building backend systems or services (Software Engineer).
5+ years of software engineering experience building and operating production-grade backend or platform systems (Senior Software Engineer).
Strong proficiency in Python (or similar languages such as Go or Java).
Experience designing and building distributed systems and scalable services.
Experience running and operating services in Kubernetes-based environments.
Familiarity with machine learning or LLM-powered applications and the challenges of running them in production.
Experience designing systems with a focus on reliability, scalability, observability, and maintainability.
Strong understanding of APIs, asynchronous processing, and service-oriented architecture.
Bachelor’s degree in Computer Science, Engineering, or related discipline, or equivalent practical experience.

Nice To Haves

Ability to navigate ambiguity, make sound technical decisions, and drive projects end-to-end.
Strong collaboration and communication skills.
Experience working on platforms, infrastructure, or developer tooling.
Familiarity with workflow orchestration or multi-step processing systems.
Experience with monitoring, logging, and observability tools.
Familiarity with cloud platforms and modern deployment practices (CI/CD).
Experience building or supporting platforms, developer infrastructure, or internal tooling.
Experience with agent-based systems, workflow orchestration, or complex multi-step pipelines.
Exposure to LLM-based applications or agent-style architectures.
Familiarity with LLM application patterns, such as: Tool integration, Retrieval-augmented generation (RAG), Context and memory management and/or Multi-step workflows
Experience with observability stacks, tracing systems, and debugging distributed workflows.
Familiarity with model serving, vector databases, or evaluation frameworks.
Experience mentoring engineers and contributing to technical direction.

Responsibilities

Build and maintain backend services that support agent execution, orchestration, and lifecycle management.
Develop systems for workflow coordination, state management, and tool integration.
Write high-quality, maintainable code in Python to power platform capabilities and APIs.
Deploy and operate services on Kubernetes, ensuring reliability and scalability.
Contribute to systems for observability, logging, tracing, and debugging of distributed workflows.
Improve system performance across latency, throughput, and fault tolerance.
Build internal tools and APIs that improve the developer experience for teams using the platform.
Collaborate with engineers, product managers, and AI teams to deliver production-ready solutions.
Participate in design discussions and contribute to system architecture and technical decisions.