Senior SOCD Applied AI Engineer

Details

NVIDIA's SOC Design (SOCD) team is seeking an Applied AI Engineer to eliminate bottlenecks in SOC integration workflows through intelligent automation. The role focuses on building AI-powered tools, agents, and automation solutions to reduce cycle time and manual effort.

The engineer will work directly with SOCD execution and methodology teams to identify workflows that can be accelerated with AI services, including RAG-grounded knowledge systems, LLM-powered assistants, and multi-step agents integrated with internal design infrastructure.

Responsibilities

• Develop LLM-powered tools for high-value execution tasks, including design review summarization, signoff status aggregation, integration checklist enforcement, CI/CD pipeline gating, and cross-team status reporting.
• Build and deploy RAG-based knowledge systems grounded in internal design documentation and execution artifacts.
• Design AI-assisted coding workflows, including agent-based development tools, reusable prompt templates, and structured skills to accelerate engineering productivity.
• Own the reliability and evaluation of AI systems, including logging, tracing, prompt regression testing, and output validation frameworks.
• Collaborate with SOCD execution and methodology teams to scope problems, validate solutions, and define metrics for productivity gains from deployed automation.

Requirements

• BS or MS in Computer Science, Computer Engineering, Electrical Engineering, or a related field, or equivalent experience.
• 6+ years of experience building production-grade software systems.
• Proven experience shipping AI- or LLM-powered applications, agents, or automation workflows into production environments.
• Strong Python skills, with the ability to design, prototype, and productize AI-enabled services, APIs, integrations, automation workflows, and internal tools.
• Practical experience building LLM-powered agents or agentic workflows, including hands-on use of Claude Code, OpenAI Codex, Cursor, or equivalent coding agents to improve development workflows.
• Hands-on experience with LLM application frameworks such as LangChain, LlamaIndex, or equivalent, and RAG architectures, including chunking, embedding models, vector databases, and retrieval design.
• Solid software engineering fundamentals and a production mindset, including system design, API design, testing, CI/CD, code quality, observability, security, databases, containers, and distributed or event-driven systems.
• Ability to identify repetitive, high-friction, or knowledge-intensive workflows and turn them into practical AI-enabled tools, automations, or assistants that improve productivity and operational efficiency.
• Demonstrated end-to-end ownership of engineering solutions, from architecture and development through deployment, integration, and ongoing operations and support.
• Excellent communication skills and a collaborative, proactive approach.

Preferred Qualifications

• Advanced AI experience, including fine-tuning or domain-specific prompt engineering, such as adapting models to understand RTL patterns.
• Experience with MCP (Model Context Protocol) or similar tool-calling standards for interoperable agent ecosystems.
• Experience with multi-agent orchestration frameworks.
• Knowledge of ASIC development and SOC integration.
• Experience building lightweight internal tools or full-stack applications, such as React and TypeScript frontends with FastAPI backends, to surface AI capabilities.

Benefits

NVIDIA offers competitive salaries, a generous benefits package, equity, and the opportunity to work with GPU and AI technology. NVIDIA is an equal opportunity employer committed to an inclusive work environment.

Applications will be accepted at least until July 28, 2026. This posting is for an existing vacancy. NVIDIA uses AI tools in its recruiting processes.