Skip to main content
NVIDIA

Software Engineer, OpenShell

NVIDIA United States Full-time 4 months ago
Embedded & Systems Software

$184,000 - $287,500 USD yearly

Originally posted July 31, 2026 by the employer.

About the role

NVIDIA OpenShell is building the runtime infrastructure for secure, scalable, production-grade AI agents. This role sits at the intersection of research, product, and engineering to integrate advances in agentic systems into enterprise runtime tools and workflows.

What you'll do

  • Follow research in tool use, planning, memory, evaluation, self-improvement, multi-agent workflows, runtime infrastructure, and agent safety/security.
  • Reproduce and test methods from research papers, open-source projects, industry work, and internal NVIDIA research.
  • Create hands-on proof-of-concepts using OpenShell, including agent harnesses, evaluation loops, self-improving workflows, and runtime-native developer experiences.
  • Design evaluation and red-team harnesses that measure agent reliability, usefulness, scalability, safety, security, and developer experience.
  • Design secure-by-default workflows for agents operating with tools, code, files, credentials, and enterprise systems.
  • Partner across engineering, product, design, research, solutions, and developer-facing teams to move prototypes into production.

What you'll need

  • 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.
  • Experience turning 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, run experiments, and communicate findings clearly.

Skills: AI agent infrastructure, LLMs, runtime infrastructure, evaluation frameworks, inference optimization

More semiconductor jobs: NVIDIA jobs

Market context

Tracked in our index since 14 Jul 2026. This is our observation date, not the employer posting date. Specialty: Infrastructure/Platform Software (Infrastructure Platform). 1056 active roles in this specialty at 98 employers in our index, as of 18 Nov 2026.

How we counted: postings read from employer career sites. How we count

Apply now
United States
Remote
Full-time
$184,000 - $287,500 USD yearly
4 months ago

Share this job