# Senior Software Engineer, Open Harness Engineering

**Company**: NVIDIA
**Work arrangement**: remote
**Experience**: senior
**Job type**: full-time
**Category**: Engineering
**Industry**: Technology

**Apply**: https://nvidia.wd5.myworkdayjobs.com/en-US/NVIDIAExternalCareerSite/job/US-CA-Remote/Senior-Software-Engineer--Open-Harness-Engineering_JR2024798?utm_source=yubhub.co&utm_medium=jobs_feed&utm_campaign=apply
**Canonical**: https://yubhub.co/jobs/job_a559a218-123

## Description

NVIDIA is seeking a Senior Software Engineer to help build core libraries, evaluation systems, and reusable harness capabilities for AI agents. The successful candidate will work on open-source agent harnesses, sandboxed execution, model-provider infrastructure, and agent benchmarks.

**Job Summary:** As a Senior Software Engineer on our Open Harness Engineering team, you will work hands-on across open-source agent harnesses, sandboxed execution, model-provider infrastructure, and agent benchmarks to help improve the next generation of agents. You will turn agent-evaluation evidence into real improvements: diagnosing failures, contributing upstream, and proving quality, reliability, cost, and latency gains across models.

**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.

**Requirements:**

- Bachelor’s or Master’s degree in Computer Science, Artificial Intelligence, Applied Math, or a related field, or equivalent experience.

- 8+ years of hands-on software-engineering experience, with demonstrated technical ownership of production systems; and architecture design leadership.

- Expert Python skills and working proficiency in Rust, Go, C++, or TypeScript, with the ability to debug systems across language and process boundaries.

- Experience building or extending LLM agents, coding agents, tool-use loops, model-provider integrations, developer tools, or evaluation infrastructure.

- Solid understanding of asynchronous execution, subprocesses, containers, sandboxing, callbacks, retries, networking, and distributed compute.

- Experience crafting reproducible experiments, benchmark methodology, performance investigations, regression gates, or reliability analysis under nondeterministic conditions.

- A record of shipping and maintaining open-source or developer-facing software with sound testing, API development, documentation, and code reviews.

**Benefits:** NVIDIA offers highly competitive salaries and a comprehensive benefits package, including equity and benefits. See www.nvidiabenefits.com/ for more information.

## Skills

### Required
- Python
- Rust
- Go
- C++
- TypeScript
- LLM agents
- coding agents
- tool-use loops
- model-provider integrations
- developer tools
- evaluation infrastructure
- asynchronous execution
- subprocesses
- containers
- sandboxing
- callbacks
- retries
- networking
- distributed compute

### Nice to have
- open-source coding agents
- harnesses
- agent runtimes
- evaluation frameworks
- observability projects
- published research
- technical writing
- patents
- substantive open-source work
- autonomous software engineering
- agent evaluation
- reliability
- tool use
- inference efficiency
- SWE-bench
- Terminal-Bench
- AgentBench
- trace-analysis and observability systems
- OpenTelemetry
- OpenInference

---

Source: [Apply at nvidia.wd5.myworkdayjobs.com](https://nvidia.wd5.myworkdayjobs.com/en-US/NVIDIAExternalCareerSite/job/US-CA-Remote/Senior-Software-Engineer--Open-Harness-Engineering_JR2024798?utm_source=yubhub.co&utm_medium=jobs_feed&utm_campaign=apply)