2 days ago
Base Salary
$184k - $357k/yr
Responsibilities
- Define and evolve technical approaches for evaluating and improving open agent harnesses across frameworks, models, and benchmark environments.
- Build and operate scalable, reproducible evaluation systems covering CI, scheduled compute, sandboxed execution, artifact provenance, trace capture, and analysis.
- Diagnose agent failures using traces, logs, tool results, and benchmark artifacts across harness, evaluator, environment, inference, and model causes.
- Design controlled experiments and promotion criteria to distinguish genuine improvements from noise, benchmark artifacts, and model-specific gains.
- Ship harness and runtime improvements, including open-source contributions, detectors, regression tests, and documentation.
- Partner with Relay, Hermes, model, infrastructure, and research teams to create 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.
- At least 8 years of hands-on software engineering experience with technical ownership of production systems and architecture design leadership.
- Expert Python skills and working proficiency in Rust, Go, C++, or TypeScript, including debugging across language and process boundaries.
- Experience building or extending LLM agents, coding agents, tool-use loops, model-provider integrations, developer tools, or evaluation infrastructure.
- Understanding of asynchronous execution, subprocesses, containers, sandboxing, callbacks, retries, networking, and distributed compute.
- Experience with reproducible experiments, benchmark methodology, performance investigations, regression gates, or reliability analysis under nondeterministic conditions.
- Record of shipping and maintaining open-source or developer-facing software with testing, API development, documentation, and code reviews.
- Preferred experience includes open-source contributions, published research or technical writing, public agent benchmarks such as SWE-bench, Terminal-Bench, or AgentBench, and trace-analysis or observability systems such as OpenTelemetry and OpenInference.
Benefits
- Competitive base salary with equity and benefits.
- Comprehensive benefits package for employees and families.
- Applications accepted at least until September 5, 2026.
Tech Stack
Categories
About Nvidia
Since its founding in 1993, NVIDIA (NASDAQ: NVDA) has been a pioneer in accelerated computing. The company’s invention of the GPU in 1999 sparked the growth of the PC gaming market, redefined computer graphics, ignited the era of modern AI and is fueling the creation of the metaverse. NVIDIA is now a full-stack computing company with data-center-scale offerings that are reshaping industry.