Autonomous Agent Engineer

Details

We're building the infrastructure that lets AI agents operate autonomously and securely at NVIDIA. This role owns the execution environments, state management systems, and security boundaries that make autonomous agents safe and reliable. The team designs and ships SDKs, CLIs, and developer tooling that turn complex sandboxing into a straightforward experience for agent builders and users across the company.

Today, "sandbox" means different things to different teams: Docker containers, microVMs, or full virtual machines, each with different security guarantees. We need someone who can navigate these tradeoffs and build a unified developer experience on top of them. This work is greenfield, and many of the problems we're solving don't have existing industry solutions.

Responsibilities

• Architect sandboxed compute environments where agents securely execute code, access tools, and interact with external services.
• Design and ship SDKs using Python and Go, as well as CLI tooling for provisioning and managing agent workloads in isolated environments.
• Create onboarding templates, reference implementations, and CLI workflows that make secure execution the default.
• Build state management for long-running agent operations, including checkpoint and recovery.
• Embed security into SDK primitives, including isolation policies, secrets injection, network policies, capability declarations, and kill switches.
• Engineer authentication integrations for workload identity, delegated tool access, and scope attenuation without static secrets.
• Build observability and audit infrastructure, including structured logs, decision traces, security telemetry, and audit trails wired into enterprise monitoring.

Requirements

• Bachelor's or master's degree in Computer Science, Engineering, or a related field, or equivalent experience.
• 8+ years of experience building distributed systems, infrastructure, or developer platforms at scale.
• Deep systems engineering skills in containers, microVMs, Kubernetes, and Linux security primitives.
• Track record of shipping developer SDKs or CLIs adopted by multiple teams.
• Experience building agents using various frameworks and harnesses in an enterprise context.
• Proficiency in Python, Go, Rust, or a similar language.

Preferred Qualifications

• Experience building execution environments for agentic AI systems or LLM applications that execute code autonomously.
• Experience with sandboxing and isolation technologies such as gVisor, Firecracker, Kata Containers, or V8 isolates.
• Strong security fundamentals, including threat modeling, authentication, least privilege, and secrets management.
• Experience designing multi-tenant execution platforms, serverless infrastructure, or sandboxed compute at scale.
• Background in durable execution patterns or checkpoint and recovery systems for long-running workloads.

Compensation and Benefits

The base salary range is USD 184,000–287,500 for Level 4 and USD 224,000–356,500 for Level 5. Base salary is determined based on location, experience, and the pay of employees in similar positions. The role is also eligible for equity and benefits.

Applications will be accepted at least until April 13, 2026. NVIDIA uses AI tools in its recruiting processes. NVIDIA is an equal opportunity employer.