Senior Software Engineer - Open Agent Harness & AI Evaluation

Nvidia Corporation in; Santa Clara (CA); On-site; USD 184,000 - 357,000; Full time

Job summary

NVIDIA in Santa Clara, CA is seeking a Senior Software Engineer to help build core libraries, evaluation systems, and reusable harness capabilities for open-agent work. You will work hands-on across open-source agent harnesses, sandboxed execution, and model-provider infrastructure to improve agent safety, speed, and reliability.

The role requires 8+ years of software engineering, expert Python, and proficiency in Rust/Go/C++/TypeScript, plus experience with distributed systems, asynchronous

Qualifications

• Bachelor's or Master's degree in CS, AI, Applied Math, or related field, or equivalent experience.
• 8+ years of hands-on software-engineering experience and architecture leadership.
• Expert Python skills; working proficiency in Rust, Go, C++, or TypeScript.
• Experience building/open-source agent harnesses, tooling, or evaluation infra.
• Solid knowledge of asynchronous execution, containers, sandboxing, networking, and distributed compute.
• Experience crafting reproducible experiments and reliability analysis.
• Shipping open-source or developer-facing software with testing and docs.

Responsibilities

• Define and evolve the technical approach for evaluating and improving open agent harnesses across frameworks, models, and benchmark environments.
• Build and operate scalable, reproducible evaluation systems spanning CI, scheduled compute, sandboxed execution, artifact provenance, trace capture, and analysis.
• Diagnose agent failures from traces, logs, tool results, and benchmark artifacts, separating harness, evaluator, environment, inference, and model causes.
• Design controlled experiments and promotion criteria that distinguish genuine harness improvements from noise, benchmark artifacts, or model-specific gains.
• Ship focused harness and runtime improvements, including upstream open-source contributions, detectors, regression tests, and maintainable documentation.
• Partner with Relay, Hermes, model, infrastructure, and research teams to turn recurring optimization needs into reusable runtime, trace, and evaluation capabilities.

Skills

Python

Rust

Go

C++

TypeScript

Open-source

Agent harnesses

Distributed systems

Asynchronous execution

Education

Bachelor’s or Master’s in Computer Science or related field

Tools

Docker

Kubernetes

OpenTelemetry

CI/CD pipelines

Job description

NVIDIA in Santa Clara, CA is seeking a Senior Software Engineer to help build core libraries, evaluation systems, and reusable harness capabilities for open-agent work. You will work hands-on across open-source agent harnesses, sandboxed execution, and model-provider infrastructure to improve agent safety, speed, and reliability.

The role requires 8+ years of software engineering, expert Python, and proficiency in Rust/Go/C++/TypeScript, plus experience with distributed systems, asynchronous