Staff AI Engineer

Summit Health•Minneapolis, MN

1d•Hybrid

About The Position

We’re hiring a Staff AI Engineer to build product features powered by modern AI models. You’ll work across our Next.js/React frontend and Go backend services to ship AI-enabled capabilities that are reliable, measurable, and valuable to the business. You’ll be leading projects and mentoring engineers in the best practices of software development. This role is ideal for a developer who can ship end-to-end features and is excited to leverage AI tools in their daily workflow (for research, prototyping, testing, and coding) while maintaining strong engineering quality. We do not expect you to be a machine learning researcher. We expect you to be a curious, pragmatic engineer who is excited to build customer facing capabilities.

Requirements

8–10 years of professional software engineering experience.
GoLang: Practical experience building backend services or APIs in Go. Understanding of goroutines, channels, structs, and Go modules.
JavaScript/TypeScript: Proficiency with React and the Next.js ecosystem (App Router, Components, Hooks, etc.).
AI/LLM Familiarity: Experience integrating LLM APIs (OpenAI, Anthropic, Gemini) into applications.
Design and implement tools that allow AI models to interact securely with our backend services, ensuring the LLM has the right context to perform tasks.
Familiarity with orchestration concepts (Google’s ADK, Vercel AI SDK, or custom orchestration).
Database Literacy: Comfortable writing SQL queries and interacting with relational databases (Postgres preferred).
Engineering Best Practices: Experience with Git version control, CI/CD basics, and writing unit tests.
AI Programming
Application Programming Interface (API)
Backend Systems
Go Programming Language

Nice To Haves

Mobile Development: Experience with React Native or Expo. Ability to deploy AI features to mobile devices and understand the constraints of mobile networks.
Advanced Data Infrastructure: Familiarity with Apache Kafka for event streaming or Redis for caching.
DevOps/Cloud: Exposure to Docker, Kubernetes, and AWS/GCP services.

Responsibilities

Design and implement full-stack features that utilize LLMs (OpenAI, Anthropic, Gemini) to solve user problems. You will build "Generative UI" elements where the AI renders interactive UI components.
Build and maintain Model Context Protocol (MCP) servers to expose internal databases, APIs, and business logic as tools for LLMs.
Using tools such as Google’s Agent Development Kit to build low-latency interfaces that stream text to the client, ensuring a responsive user experience even with slow models.
Leading a team of developers to build new features on the web and mobile experience. Designing solutions and driving consensus between different teams.
Write robust, high-performance Go code to orchestrate AI services. You will use goroutines to manage concurrent agent execution and handle long-running third-party API calls efficiently.
Design and implement RESTful and gRPC APIs that serve as the interface between our frontend and the AI models.
Collaborate on integrating Kafka and Redis to build asynchronous message processing pipelines. You will help decouple AI agents, allowing them to communicate via events rather than direct calls.
Ensuring dashboards are set up for monitoring services to help debug issues during on-call incidents troubleshooting.
Actively use AI coding assistants (e.g., GitHub Copilot, Cursor, etc.) to accelerate boilerplate code generation, unit testing, and documentation. You will be expected to use these tools to multiply your output.
Critically evaluate and debug AI-generated code. You are the gatekeeper of quality; you must understand every line of code committed, ensuring it meets security and performance standards. You will fix errors in code logic.
Iteratively refine system prompts to ensure consistent, safe, and high-quality model outputs. You will write automated "Evals" to test the AI's performance against regression.