← All roles

Software Engineer, OpenShell

NVIDIA· Engineer, Sys SW
Apply on company site
Hybrid (Remote - US)$184k - $287.5kfull-timePosted 3mo ago

About the role

OpenShell Research Engineer at NVIDIA focuses on translating AI research into secure, production-grade agent infrastructure. Role blends research, product, and engineering to bring advances in agentic systems into runtime, tools, and workflows for enterprise use.

Responsibilities

  • Track the cutting edge of agentic systems and related areas (tool use, planning, memory, evaluation, self-improvement, multi-agent workflows, runtime infrastructure, agent safety/security)
  • Bridge research and product by identifying ideas that improve OpenShell and translating them into concrete product opportunities
  • Benchmark and adapt by reproducing and testing promising methods from papers, open-source projects, industry work, and internal NVIDIA research
  • Build rapid prototypes and hands-on proofs-of-concept using OpenShell (agent harnesses, evaluation loops, self-improving workflows, runtime-native developer experiences)
  • Red-team systems by designing evaluation and red-team harnesses measuring reliability, usefulness, scalability, safety, security, and developer experience
  • Secure the workflow by designing secure-by-default workflows for agents operating with tools, code, files, credentials, and enterprise systems
  • Partner across teams by collaborating with engineering, product, design, research, solutions, and developer-facing teams to move ideas from prototype to product

Qualifications

  • 8+ years of professional practical experience in research engineering, software development, or a related technical field
  • MS/PhD in Computer Science, Physics, or a related field or equivalent experience
  • Strong background turning complex research into reusable products, tools, demos, benchmarks, or production systems at scale
  • Deep experience in several of: LLMs, agent harnesses, multimodal generative models, evaluation frameworks, synthetic data generation, post-training, inference infrastructure/optimization, adversarial ML, or agent safety/security
  • Demonstrated ability to drive independent technical investigation (survey relevant work, run experiments, form a clear point of view, communicate findings)
  • Strong product sense and care for UX and AX (developer-friendly tools and ergonomic agent experiences)
  • Focus on real-world impact (enterprise capabilities, reference implementations, developer workflows, or product improvements)
  • Outstanding collaboration across research, engineering, product, design, solutions, and developer-facing teams

Skills

Required:Agent harnessesEvaluation frameworksAI safety/security
Nice to have:Multimodal generative modelsSecure-by-default workflowsPost-training / inference optimizationOpen-source software

Benefits

  • equity
  • benefits (see NVIDIA benefits page)
Last updated Aug 7, 2026. Interested? Apply on the company site.

About NVIDIA

World Leader in AI Computing

NVIDIA invents the GPU and drives advances in AI, HPC, gaming, creative design, autonomous vehicles, and robotics.

AIautonomous vehiclesgaminggpugraphics cardhigh performance computingliquid-ai-recruiting-targetllm
Company profileWebsite

More open roles at NVIDIA