Staff Engineer, Storage Metadata and Context

Pixar Animation Studios • Emeryville, CA

4d • $182,835 - $236,610

About The Position

As a Staff Engineer at the intersection of Data Platforms and AI, you will architect software layers that make production-facing storage context-aware. You will design APIs, metadata services, and Model Context Protocol (MCP) implementations that enable AI agents to navigate and reason across petabytes of media assets, bridging traditional HPC protocols with modern agentic systems. The role collaborates across technical storage teams, software tool designers, and creative artists to turn creative workflows into practical technical solutions.

The position involves exposing existing NAS environments through modern API abstractions and MCPs; building systems that extract context from storage hierarchies and file headers; maintaining synchronization between raw file data and metadata representations; and enabling capabilities such as auto-tagging, similarity search, and automated summarization. Participation in an on-call rotation for critical issues is required.

Requirements

• Experience architecting, managing, and troubleshooting physical and/or virtual storage solutions, and applying that knowledge to agentic workflows and metadata pipelines at petabyte scale.
• Expertise in NFS, SMB, and S3, including file locking, permissions, and latency considerations across protocols.
• Proven experience building REST or gRPC APIs and middleware between raw storage and application layers.
• Understanding of MCP and how to build tool-calling interfaces for LLMs.
• Proven ability to design metadata schemas and indexing pipelines using technologies such as Kafka, ElasticSearch, or vector databases.
• At least 3 years of recent experience in scale environments transitioning manual workflows into programmatic, API-driven services.
• Ability to translate creative needs into technical metadata queries that return precise results.
• Comfort working across programming languages to connect storage metrics and file data to agentic frameworks.

Nice To Haves

• Deep proficiency in Python is a significant plus.
• Hands-on experience with agentic libraries, custom data connectors, and Retrieval-Augmented Generation (RAG) architectures.
• Experience with Docker and Kubernetes for scaling metadata extraction and embedding workers.
• Understanding of high-end storage performance characteristics, including Vast, NetApp, StorageGrid, and AWS, and ways to minimize metadata-operation overhead.
• Interest in digital content creation and how AI can modernize production workflows.

Responsibilities

• Develop and maintain software layers exposing NAS environments, including NFS, SMB, and S3, to AI agents and LLM frameworks through API abstractions and MCPs.
• Lead implementation of MCP servers that provide AI models a standardized way to browse, read, and interpret data in HPC storage.
• Design systems that extract context from long-path hierarchies and file headers, and build REST, gRPC, and MCP connections for AI agents to resolve creative queries.
• Collaborate across storage teams, software tool designers, and creative artists, translating technical concepts into workflow-enhancing solutions for non-technical users.
• Manage the state and relationships between raw file data and its digital twin in the metadata layer, keeping relational and semantic data synchronized as the studio library evolves.
• Enable storage features such as auto-tagging, similarity search, and automated summarization.
• Participate in an on-call rotation for critical issues.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed