Software Engineer - Agent Harness

Job Summary

We are building an agent framework that supports hybrid local and cloud AI models. The role focuses on designing and implementing the harness that manages context, tool invocation, scheduling, security, and observability.

• Design and build the agent loop: planning, tool invocation, observation handling, retries, and termination.
• Implement integrations with file I/O, terminal execution, web services, and other tooling.
• Build context management and memory strategies for efficient use of model windows.
• Develop scheduling for automatic and background task execution.
• Ensure the harness is model‑agnostic so local and cloud models are interchangeable.
• Define security mechanisms for the agent loop.
• Provide observability, debugging, tracing, replay, and reproducibility features.

Required:

• BS/MS in CS, EE, Math or related STEM field.
• 5+ years of software development experience.
• Strong programming skills in Python, Type Script, Go, Rust, or C++.
• Experience with async, concurrency, and process/subprocess management.
• History of building tools that invoke external APIs in loops and handling failure modes.
• Proficiency in reading and working with unfamiliar codebases.

Preferred:

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

Annual Salary Range: $170,500 – $315,490 USD (US locations). Compensation includes competitive base pay, stock bonuses, and benefit programs covering health, retirement, and vacation.

All qualified applicants will receive consideration for employment without regard to race, color, religion, sexual orientation, gender identity, or any other characteristic protected by law.