Senior AI Engineer, Platform Engineering

ResMed•Halifax, NS

About The Position

Global Technology Solutions (GTS) at ResMed is a division dedicated to creating innovative, scalable, and secure platforms and services for patients, providers, and people across ResMed. The primary goal of GTS is to accelerate well-being and growth by transforming the core, enabling patient, people, and partner outcomes, and building future-ready operations. The strategy of GTS focuses on aligning goals and promoting collaboration across all organizational areas. This includes fostering shared ownership, developing flexible platforms that can easily scale to meet global demands, and implementing global standards for key processes to ensure efficiency and consistency. About the Role: We are seeking a Senior AI Engineer – Platform Engineering to design, build, and deploy intelligent agent-based solutions that solve business and engineering problems. You will leverage cloud-native and AI platform capabilities to develop production-grade AI applications, autonomous workflows, and Retrieval-Augmented Generation (RAG) solutions that improve productivity, automate complex processes, and enhance decision-making across the organization. This role requires a strong blend of software engineering, AI application development, systems integration, and solution architecture. The ideal candidate has hands-on experience building AI agents, Retrieval-Augmented Generation (RAG) solutions, and tool-driven workflows using modern LLM frameworks.

Requirements

5+ years of experience in Software Engineering, Platform Engineering, or Cloud Engineering
Hands-on experience building AI applications using frameworks such as LangGraph, Strands Agents, OpenAI Agents SDK, or similar agent orchestration frameworks.
Strong programming skills in TypeScript, Go and/or Python
Experience designing and building microservice applications
Experience integrating APIs and enterprise systems
Hands-on experience building production AI applications using LLMs
Strong understanding of Retrieval-Augmented Generation (RAG)
Strong understanding of Vector databases and embeddings
Strong understanding of Tool calling and agent orchestration
Strong understanding of Structured outputs, context engineering, and agent orchestration
Strong understanding of AI evaluation and observability

Nice To Haves

Experience building AI copilots, digital assistants, or autonomous agents
Experience integrating AI solutions with GitHub, Jira, Slack, Datadog, Confluence, or similar enterprise platforms
Experience with vector databases such as OpenSearch
Experience with AI observability and evaluation tools such as Langfuse or Datadog LLM Observability
Experience building MCP servers and agent interoperability patterns
Experience with Kubernetes and cloud-native platforms

Responsibilities

Design, build, and deploy AI agents and agentic workflows that solve business and engineering challenges using modern LLM frameworks.
Develop AI-powered applications leveraging Retrieval-Augmented Generation (RAG), vector databases, embeddings, tool calling, and agent orchestration patterns.
Optimize retrieval quality and response accuracy through chunking strategies, metadata enrichment, hybrid search, reranking, evaluation, and continuous improvement.
Integrate AI solutions with enterprise platforms such as GitHub, Jira, Confluence, Datadog, Slack, Kubernetes, and internal APIs.
Develop reusable connectors, tools, and agent capabilities that enable agents to retrieve information and perform actions across systems.
Establish best practices for testing, evaluation, observability, security, and governance of AI applications.
Monitor and optimize agent performance, reliability, latency, accuracy, and cost while troubleshooting production issues and continuously improving solution quality.