Senior Staff Software Engineer - AI Agent Platform

NVIDIA•Us, CA

22h

About The Position

Design, build, and scale the infrastructure powering NVIDIA’s AI agent ecosystem. This role sits at the intersection of distributed systems, developer platforms, and agentic AI, building foundational services that enable teams across the company to develop, deploy, orchestrate, and operate autonomous AI agents at production scale. The position involves creating agent lifecycle platform services, Kubernetes execution environments, CI/CD systems, framework-agnostic infrastructure, messaging and data services, session management, authentication, and secrets management. The engineer will also partner with security teams on compliance, access controls, and approval workflows. The role requires a bachelor's or master's degree in Computer Science, Engineering, or a related field, or equivalent experience, and 12+ years in software engineering. The base salary range is $200,000–$322,000 for Level 5 and $248,000–$391,000 for Level 6. The role is also eligible for equity and benefits. Applications will be accepted at least until October 20, 2026. This posting is for an existing vacancy.

Requirements

Bachelor's or master's degree in Computer Science, Engineering, or a related field, or equivalent experience.
12+ years in software engineering, ideally in platform engineering, infrastructure, or developer tools.
Experience building and scaling AI agents in production using frameworks such as Claude Code, Codex, or LangGraph.
Deep Kubernetes expertise, including pod orchestration, persistent storage, RBAC, and multi-cluster management.
Strong Python skills and production API experience using FastAPI, Flask, or similar asynchronous frameworks.
Proven track record designing distributed systems with Kafka, Redis, and MongoDB or PostgreSQL.
Expertise building and managing robust CI/CD pipelines using GitLab CI and ArgoCD for continuous delivery to Kubernetes.
Experience designing AI data platform components, including ingestion pipelines, vector stores, retrieval APIs, and data preprocessing workflows, and building developer-facing platform APIs consumed by multiple engineering teams.
Solid understanding of authentication and identity, including OAuth 2.0, JWT, token exchange, and secrets management with Vault.
History of leading sophisticated technical projects, such as migrations or greenfield platform builds, with strong interpersonal skills to drive alignment across teams and write clear design documents.

Nice To Haves

Experience building or operating AI agent platforms or agentic workflow systems, with hands-on expertise in agent protocols and frameworks such as MCP, A2A, LangChain, or LangGraph.
Hands-on experience with RAG architectures, embedding pipelines, and vector databases such as Milvus, Pinecone, or Weaviate.
Full-stack skills with React or Vue for building developer portals and dashboards.
Contributions to open-source infrastructure or platform tooling.

Responsibilities

Build and develop platform services managing the full agent lifecycle, from registration through deployment, execution, and teardown.
Architect multi-tenant Kubernetes execution environments with pod lifecycle management, per-tenant namespace isolation, persistent storage, admission policy enforcement, and identity propagation.
Develop and maintain automated CI/CD pipelines using GitLab CI and ArgoCD, including reusable pipeline templates and deployment blueprints for standardizing agent builds.
Build framework-agnostic infrastructure for multiple agent SDKs and harnesses, including lifecycle hooks, skills configuration, memory services, and OTEL instrumentation.
Build and operate Kafka-based message pipelines and real-time event streaming using Redis PubSub and SSE.
Develop data ingestion pipelines, access interfaces, and storage layers for AI agent knowledge and context.
Implement session management for state persistence, conversation history, and agent recovery across sessions.
Develop multi-layer authentication using OAuth 2.0, JWT validation, token exchange, and gateway integration; manage the secrets lifecycle with Vault, including provisioning, rotation, and container injection.
Partner with security teams on compliance, access controls, and approval workflows for agent operations.
Lead sophisticated technical projects, such as migrations or greenfield platform builds, and drive alignment across teams through interpersonal skills and clear design documents.