This role focuses on building the harness for an agent framework that combines local and cloud intelligence. The team aims to create a model-agnostic system that efficiently manages context, tool invocation, and scheduling. You will partner with the SRE/Production squad to ensure reliable operation in production. The position emphasizes curiosity and growth in architecting frontier agent harnesses and understanding LLM agents.

• BS/MS in Computer Science, Electrical Engineering, Mathematics, or a related STEM field
• 5+ years of software development experience
• Proficiency in at least one programming language such as Python, TypeScript, Go, Rust, or C++
• Comfort with asynchronous programming, concurrency, and process management
• Experience building projects that call external tools or APIs in a loop and handle failure modes
• Ability to read and understand unfamiliar codebases and runtime environments

• Design and build the agent loop including planning, tool invocation, and observation handling
• Implement tool integrations for file I/O, terminal execution, and web services
• Develop context management strategies for summarization and memory usage
• Implement scheduling and automatic background task execution
• Ensure the harness remains model-agnostic for local and cloud models
• Design security mechanisms for the agent framework
• Make the agent loop observable and debuggable through tracing and replay capabilities

• Intel offers a comprehensive benefits package including competitive pay, stock programs, healthcare coverage, retirement plans, paid time off, parental leave, and programs supporting employee wellbeing and professional development.