Software Engineer - Agent Harness

Intel Corporation•Santa Clara, CA

12d•$170,500 - $315,490•Hybrid

About The Position

Our Mission At Intel, our journey is to transform AI into something safer, more trustworthy, and respectful of human privacy by design. We believe transformative AI should have a positive impact on people—powerful in capability, yet honest about its limits and protective of the data and resources it touches. To get there, we build agentic AI that combines the best of local and cloud intelligence — private, affordable, and sustainable by design. Small, efficient models run directly on the user's machine (AI PC, edge, on-prem, and beyond), keeping data private and token costs low, while powerful cloud models handle the hardest work: planning, reasoning, and complex problem-solving. Today, neither approach can deliver this alone. Together, they give people real capability without compromise—data stays private, spend stays predictable, and energy use stays in check. We're building intelligence that scales without sacrificing trust, cost, or the planet—because the future of AI should belong to the people it serves. Role Summary The model is only half an agent; the harness is the other half. You build everything around the model that makes it act — context management, tool and function calling, file and terminal execution, scheduling, memory, and the agent loop itself. This is core product engineering on an agent framework comparable to well know AI models, but built to run hybrid (local + cloud) and with efficiency.

Requirements

BS/MS in CS, EE, Math or related STEM field
5+ years software development background
Strong in at least one of Python, TypeScript, Go, Rust, C++
Comfortable with async, concurrency, and process / subprocess management
Has built a project that calls external tools or APIs in a loop and handled the failure modes
Experienced at reading unfamiliar codebases and someone else’s runtime

Nice To Haves

Experience with agent frameworks, tool / function calling, or MCP
Built developer tooling, CLIs, or IDE-adjacent products
Familiarity with sandboxing, containerization, and safe code execution
Contributions to open-source agent / LLM tooling
Experience with agent security

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