Senior AI Agent Harness Engineer

Intel; Phoenix (AZ); Hybrid; USD 195,200 - 361,200; Full time

Job summary

Intel in the United States is seeking an experienced software engineer to build and maintain the agent harness for hybrid AI workloads. You will design the loop, integrate tools, manage context, and ensure secure, observable operation.

You will work with Python, TypeScript, Go, Rust, and C++, handle async patterns, and optimize for reliability. This role offers a hybrid work model with strong compensation and opportunities to impact next-gen AI infrastructure.

Qualifications

• BS/MS in CS, EE, Math or related STEM field.
• 8+ years software development background.
• Strong command of Python, TypeScript, Go, Rust, C++.
• Expertise with async, concurrency, and process / subprocess management.
• Experience with projects that call external tools or APIs in a loop and handle failure modes.
• Experience reading unfamiliar codebases and runtimes.

Responsibilities

• Design and build the agent loop: planning, tool invocation, observation handling, retries, termination.
• Implement tool integrations — file I/O, terminal / shell execution, web, MCP servers, message apps.
• Build context management: what goes in the window, when to summarize, how to use long / cross-session memory.
• Implement scheduling and automatic / background task execution.
• Keep the harness model-agnostic so local and cloud models are swappable behind one abstraction.
• Design agent security mechanisms through different approaches.
• Make the loop observable, debuggable: tracing, replay, and reproducible agent sessions.

Skills

Python

TypeScript

Go

Rust

C++

Education

BS/MS in CS, EE, Math or related STEM field

Tools

MCP framework

Docker

Job description

Intel in the United States is seeking an experienced software engineer to build and maintain the agent harness for hybrid AI workloads. You will design the loop, integrate tools, manage context, and ensure secure, observable operation.

You will work with Python, TypeScript, Go, Rust, and C++, handle async patterns, and optimize for reliability. This role offers a hybrid work model with strong compensation and opportunities to impact next-gen AI infrastructure.