Senior Staff Software Engineer - Enterprise AI Platform
$224k - $431k • Remote • US, CA, Santa Clara
Posted 12d ago
Job Location
US, CA, Santa Clara
Tech Stack
Remote Work Policy
Fully remote
Categories
AI Agent Engineer
About the job
We are building a platform for long-running autonomous agents to operate safely within NVIDIA's enterprise. These agents are deployed in the cloud, running continuously at scale on shared accelerated compute, and perform real work across enterprise systems. This role focuses on defining the core constructs for agent development, including blueprints, tools, skills, plugins, runtime safety harnesses, and integrations with credential management, sandboxing, memory, and observability. The team designs and ships these building blocks to enable agent developers across the company to quickly set up and run agents for extended periods, ensuring security and safe execution out-of-the-box. The platform aims to abstract differences between various agent harnesses (e.g., Claude, Codex, open-source) so that skills, safety policies, and traces function consistently across them. We are enabling agents that act on behalf of users, are governed and secure, and continuously evaluate and self-improve, coordinating and handing off work with identity and policy persistence across all interactions.
Responsibilities
- Design agent blueprints with clean interfaces for authorization, sandbox, memory, observability, and skills.
- Build the runtime safety harness, including a policy engine, rate and budget caps, circuit breakers, approval gates, action allow-lists, and a kill switch.
- Enable composing and orchestrating agents, including skills as first-class units, multi-agent orchestration, and support for headless, long-running agents.
- Broker credentials for multi-agent systems to authenticate and authorize without direct secret exposure, with least-privilege scoping.
- Provide checkpoint and recovery mechanisms for agents to resume cleanly after failures.
- Instrument observability and evaluation across harnesses, including decision-level traces, cost anomaly alerts, and quality scoring.
- Close the loop by translating evaluation signals into insights for agent improvement.
- Share responsibility for keeping the platform healthy and reliable, including participating in an on-call rotation.
Requirements
- BS or MS in Computer Science, Engineering, or related field (or equivalent experience).
- 12+ years building distributed systems, infrastructure, or developer platforms at scale.
- Hands-on experience building agents on a harness, exposing them as APIs, and shipping them with CI/CD.
- Experience deploying and operating long-running services on container orchestration platforms.
- Experience with building blocks of scalable systems: messaging, caching, and durable storage.
- Proficiency in Python, Go, Rust, or similar.
Benefits
- Equity
- Benefits