Senior Software Engineer, Open Harness Engineering

NVIDIA•US, CA, Remote, TX

2d•$184,000 - $356,500

About The Position

NVIDIA is hiring a Senior Software Engineer to build core libraries, evaluation systems, and reusable harness capabilities that help make AI agents safer, faster, and easier for developers to trust. The role involves hands-on work across open-source agent harnesses, sandboxed execution, model-provider infrastructure, and agent benchmarks. The engineer will use evaluation evidence to diagnose failures, contribute improvements upstream, and demonstrate quality, reliability, cost, and latency gains across models.

Requirements

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

Nice To Haves

Meaningful contributions to open-source coding agents, harnesses, agent runtimes, evaluation frameworks, developer tools, or observability projects.
Published research, technical writing, patents, or substantive open-source work in autonomous software engineering, agent evaluation, reliability, tool use, or inference efficiency.
Experience with SWE-bench, Terminal-Bench, AgentBench, or comparable public agent benchmarks.
Shipped improvements to context management, tool interfaces, retries, sandboxed repository execution, long-running agent loops, or evaluation environments.
Experience with trace-analysis and observability systems such as OpenTelemetry, OpenInference, structured event pipelines, exporters, or debugging tools.

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 using traces, logs, tool results, and benchmark artifacts, distinguishing harness, evaluator, environment, inference, and model causes.
Design controlled experiments and promotion criteria to 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.