Description
We are building a platform that enables long-running autonomous agents to operate safely inside NVIDIA's enterprise. These agents are not assistants on a developer's laptop, but rather fleets of agents deployed in the cloud, running continuously at scale on shared accelerated compute.
The platform defines the constructs that agents are built from, including blueprints, tools, skills, and plugins that power them against enterprise data, as well as the runtime safety harness that keeps them in bounds.
As an Autonomous Agent Platform Engineer, you will design and build the platform that agent builders across NVIDIA depend on. Your responsibilities will include:
- Designing agent blueprints with clean interfaces for authorization, sandbox, memory, observability, and skills
- Building the runtime safety harness, including policy engine, rate and budget caps, circuit breakers, approval gates, action allow-lists, and kill switches
- Enabling composing and orchestrating agents, including skills as first-class units with declarative manifests, multi-agent orchestration for delegation and handoff, and support for headless, long-running, autonomous agents
- Brokering credentials so multi-agent systems can authenticate and authorize without ever touching secrets
- Providing checkpoint and recovery so an agent resumes cleanly after a crash or restart
- Instrumenting observability and evaluation that span harnesses, including decision-level traces with correlation IDs, cost anomaly alerts, and quality scoring
The team shares responsibility for keeping the platform healthy and reliable, including taking part 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 the building blocks of scalable systems, including messaging, caching, and durable storage
- Proficiency in Python, Go, Rust, or similar
Nice to have:
- Built a safety or policy engine that enforces rules on agent actions at runtime
- Designed evaluation and feedback loops for agent behavior
- Applied security fundamentals like threat modeling, authentication and authorization, least privilege, secrets management, and token exchange
- Designed AI data platform components like ingestion pipelines, vector stores, and retrieval APIs
- Shipped platform building blocks adopted by multiple engineering teams
The base salary range for this position is $200,000 - $322,000 USD per year. You will also be eligible for equity and benefits.