Senior Staff Software Engineer - Enterprise AI Platform

Requirements:

• Bachelors or masters degree in computer science, engineering, or a related discipline, or equivalent experience
• 12+ years of experience building distributed systems, infrastructure, or developer platforms at scale
• Practical experience creating agents on a harness, exposing them through APIs, and delivering them with CI/CD
• Experience deploying and operating long-running services on container orchestration platforms
• Experience with scalable-system components such as messaging, caching, and durable storage
• Proficiency in Python, Go, Rust, or a similar language
• Preferred: Experience building runtime safety or policy engines for agent actions, including approval gates and kill switches
• Preferred: Experience designing agent evaluation and feedback loops, including systems that improve agents using evaluation and production signals
• Preferred: Knowledge of security fundamentals, including threat modeling, authentication, authorization, least privilege, secrets management, and token exchange
• Preferred: Experience designing AI data platform components such as ingestion pipelines, vector stores, and retrieval APIs
• Preferred: Experience delivering platform components adopted by multiple engineering teams and leading complex technical projects, including migrations or greenfield builds

Responsibilities:

• Design agent blueprints with interfaces for authorization, sandboxing, memory, observability, and skills so agents can use enterprise integrations provided by our platform
• Build runtime safeguards, including policy checks, rate and budget limits, circuit breakers, approval gates, action allow-lists, and emergency shutdown controls
• Develop agent composition and orchestration capabilities, including declarative skills, delegation and handoffs between agents, and support for headless, long-running autonomous agents
• Broker credentials so multi-agent systems can authenticate and authorize securely without accessing secrets, while applying least-privilege token scopes
• Provide checkpointing and recovery so agents can resume after crashes or restarts
• Build cross-harness observability and evaluation, including decision-level traces, correlation IDs, cost-anomaly alerts, and quality scoring for skills, agents, and products
• Use evaluation and production telemetry to generate insights that improve agent performance
• Share responsibility for platform health and reliability, including participating in an on-call rotation

Technologies:

• AI
• CI/CD
• Support
• Python
• Rust
• Security
• Cloud

More

We are building NVIDIAs enterprise platform for secure, long-running autonomous agents operating at scale on shared accelerated compute. Our team creates the common building blocks that let agent developers across NVIDIA—including engineering, finance, legal, and HR teams—launch agents with enterprise integrations, safety, and security built in. The platform aims to provide consistent skills, policies, and observability across different agent harnesses, while supporting coordination, continuous evaluation, and improvement from production signals. The role offers a base salary range of $224,000–$356,500 for Level 5 or $272,000–$431,250 for Level 6, determined in part by location, experience, and comparable employee pay, as well as eligibility for equity and benefits. Applications are expected to be accepted at least through October 11, 2026; this is an existing vacancy. We use AI tools in our recruiting processes and are committed to an inclusive, equal-opportunity workplace.

last updated 43 week of 2026