Software Engineer, OpenShell

Details

Translate groundbreaking AI research into secure, production-grade systems for the next generation of AI agent infrastructure. NVIDIA OpenShell is building runtime infrastructure for secure, scalable, production-grade AI agents. This role sits at the intersection of research, product, and engineering, helping identify, validate, prototype, and integrate advances in agentic systems into products, tools, and workflows for enterprise builders.

Responsibilities

• Track advances in agentic systems, including tool use, planning, memory, evaluation, self-improvement, multi-agent workflows, runtime infrastructure, and agent safety and security.
• Identify research ideas that can meaningfully improve OpenShell and translate them into concrete product opportunities.
• Reproduce and test promising methods from academic papers, open-source projects, industry work, and internal NVIDIA research.
• Build rapid proof-of-concepts using OpenShell, including agent harnesses, evaluation loops, self-improving workflows, and runtime-native developer experiences.
• Design evaluation and red-team harnesses to measure agent reliability, usefulness, scalability, safety, security, and developer experience.
• Help design secure-by-default workflows for agents operating with tools, code, files, credentials, and enterprise systems.
• Collaborate with engineering, product, design, research, solutions, and developer-facing teams to move ideas from prototype to product.

Requirements

• 8+ years of professional practical experience in research engineering, software development, or a related technical field.
• MS or 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 the following areas: LLMs, agent harnesses, multimodal generative models, evaluation frameworks, synthetic data generation, post-training, inference infrastructure and optimization, adversarial ML, or agent safety and security.
• Ability to drive independent technical investigations by surveying relevant work, running experiments, forming a clear point of view, and communicating findings clearly.
• Strong product sense and care for user experience and agent experience; tools should be intuitive for developers and ergonomic for agents.
• Focus on translating research into enterprise capabilities, reference implementations, developer workflows, or product improvements.
• Outstanding team orientation and comfort collaborating across research, engineering, product, design, solutions, and developer-facing teams.

Preferred Qualifications

• Experience with secure agent runtimes, tool sandboxing, capability-based security, or enterprise policy systems.
• Experience with compliance or enterprise governance requirements such as auditability, data retention, access control, SOC 2, HIPAA, GDPR, or regulated deployment environments.
• Experience with LLM inference infrastructure, model serving, or inference optimization using Triton, TensorRT-LLM, vLLM, SGLang, Ray, Kubernetes, or cloud GPU platforms.
• Experience integrating inference backends into agentic systems, including model routing, tool-aware context management, streaming, structured outputs, retries, monitoring, and cost and performance optimization.
• Experience developing or maintaining open-source software in AI agents, LLM systems, developer tooling, ML infrastructure, model serving, or related areas.

Benefits

• Base salary range of USD 184,000–287,500 per year, determined by location, experience, and pay for similar positions.
• Equity and benefits.
• NVIDIA is committed to fostering an inclusive work environment and is an equal opportunity employer.