Software Engineer - Agent Harness (AI)

TL;DR

Software Engineer - Agent Harness (AI): Designing and building the core framework that enables AI models to act, including context management and tool execution with an accent on hybrid local and cloud hirify.globalligence. Focus on architecting the agent loop, ensuring tool-call reliability, and optimizing context-window economics.

Location: Hybrid; must be based in the US (Santa Clara, Phoenix, Folsom, or Hillsboro)

Salary: $170,500 - $315,490 USD

Company

hirify.global's Client Computing Group focuses on transforming AI into something safer, more trustworthy, and private by building agentic AI that combines local and cloud hirify.globalligence.

What you will do

• Design and build the agent loop, including planning, tool invocation, observation handling, and termination.
• Implement tool integrations for file I/O, terminal/shell execution, web, MCP servers, and message apps.
• Build context management systems, including window optimization and cross-session memory.
• Implement scheduling and background task execution.
• Maintain a model-agnostic harness allowing local and cloud models to be swappable.
• Design agent security mechanisms and implement observability tools like tracing and replay.

Requirements

• BS/MS in CS, EE, Math, or a related STEM field.
• 5+ years of software development experience.
• Strong proficiency in at least one of: Python, TypeScript, Go, Rust, or C++.
• Comfortable with async, concurrency, and process/subprocess management.
• Proven experience building projects that call external tools or APIs in a loop.

Nice to have

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

Culture & Benefits

• Total compensation package including competitive pay and stock bonuses.
• Comprehensive health, retirement, and vacation programs.
• Hybrid work model allowing a split between on-site and off-site work.