Senior AI Platform Architect (Remote)

D-Wave; United States; Remote; USD 167,000 - 230,000; Full time

Job summary

D-Wave is seeking a Staff AI Platform Developer to architect and build internal AI tooling, including LLM applications, agents, RAG systems, and workflow automation. You’ll work across teams to deploy production-ready services that securely access internal data and integrate with key tools like GitHub, Jira, and Slack.

You will guide data handling guardrails, privacy, latency, and cost, while promoting responsible AI practices and sharing knowledge across engineering teams.

Qualifications

• 7+ years of professional software/ platform engineering experience.
• Experience across the LLM application stack including RAG and tool use.
• Proficiency in Python and TypeScript/JavaScript.
• Experience designing REST APIs and backend services.
• Strong DevOps, Linux/Unix, and containerized deployments.

Responsibilities

• Lead architecture and development of internal AI tooling.
• Build and productionize LLM applications, agents, and workflows.
• Integrate tools with GitHub, Jira, Slack, and docs platforms.
• Define guardrails for data handling, security, and cost.
• Drive adoption of AI capabilities across product teams.

Skills

Python

TypeScript/JavaScript

LLM stack

prompt engineering

RAG

embeddings

vector search

reranking

context management

tool use

agent orchestration

MCP/ACP

APIs

CI/CD

Linux/Unix

containers

Git

Jira

Slack

Confluence

Docker

Kubernetes

Terraform

AWS

Education

Bachelor’s degree in Computer Science or related

Tools

Git

GitHub

CI/CD tooling

Slack

Jira

Confluence

Docker

Kubernetes

Terraform

AWS

Job description

D-Wave is seeking a Staff AI Platform Developer to architect and build internal AI tooling, including LLM applications, agents, RAG systems, and workflow automation. You’ll work across teams to deploy production-ready services that securely access internal data and integrate with key tools like GitHub, Jira, and Slack.

You will guide data handling guardrails, privacy, latency, and cost, while promoting responsible AI practices and sharing knowledge across engineering teams.