Staff Engineer, Storage Metadata and Context

Pixar Animation Studios Inc.; Emeryville (CA); Hybrid; USD 183,000 - 237,000; Full time

Job summary

Pixar Animation Studios Inc. is seeking a Staff Engineer to architect a storage metadata and context layer for AI-enabled asset management. You will shape APIs and MCP implementations to let AI agents navigate Petabytes of media. The role bridges storage, tooling, and creative teams in a hybrid Emeryville environment.

You will drive semantic discovery, contextual reasoning, and on-call readiness while aligning data with evolving creative workflows and agentic architectures.

Qualifications

• 3+ years of software-driven infrastructure in scale environments.
• Experience bridging data center storage and AI agent workflows.
• Proven API/middleware development between storage and app layers.
• Knowledge of MCP and tool-calling interfaces for LLMs.
• Design schemas and indexing pipelines for semantic representations of files.
• Ability to translate creative needs into metadata queries.
• Comfort across multiple programming languages, especially Python.

Responsibilities

• Architect semantic connectivity exposing NAS environments to AI agents and LLMs.
• Lead MCP server implementations for safe, efficient data browsing by models.
• Design semantic discovery systems for long-path hierarchies and file headers.
• Bridge storage teams, tooling designers, and artists to deliver workflow enhancements.
• Manage state and relationships between raw data and metadata reflections.

Skills

Full-Stack Storage

API & Middleware

MCP & AI Tooling

Metadata Engineering

Backend Development

Translator Mindset

HPC & Storage Knowledge

Python Proficiency

Modern AI Frameworks

Tools

Kafka

ElasticSearch

Vector DBs

REST

gRPC

Docker

Kubernetes

Job description

Staff Engineer, Storage Metadata and Context### Staff Engineer, Storage Metadata and ContextApply: Hybrid: Emeryville: Full time: Posted 2 Days Ago: R-04164Every great creative project needs a spark—and we’re the team that collaborates to support and organize the digital media behind the magic. As our data scales, we want to close a growing context gap between our technical storage hierarchies and the natural language of our creative teams. As a Staff Engineer at the intersection of Data Platforms and AI, you will architect the software layers that enable our production-facing storage to become context-aware. Your mission is to design the APIs, Metadata services, and MCP implementations that allow AI agents to navigate and reason across Petabytes of high-value media assets. You will help to bridge the gap between traditional HPC protocols and a modern Agentic ecosystem.**RESPONSIBILITIES:** * **Architect Semantic Connectivity:** Develop and maintain the software layer that exposes existing NAS environments (NFS, SMB, S3) to AI agents and LLM frameworks through modern API abstractions and MCPs* **Implement Model Context Protocol (MCP):** Lead the implementation of MCP servers to provide a standardized interface for AI models to safely and efficiently browse, read, and interpret data within our HPC storage* **Semantic Discovery & Agentic Connectivity:** Design automated systems to deconstruct the implicit context stored in long-path hierarchies and file headers, architecting the \"connective tissue\" (REST, gRPC, MCP) that enables AI agents to resolve complex creative queries without needing direct knowledge of underlying mount paths or protocols* **Cross-Disciplinary Collaborator:** Act as a critical \"bridge\" across technical storage teams, software tool designers, and creative artists—adapting your communication style to translate deeply technical concepts into practical, workflow-enhancing solutions for non-technical users* **Data & Metadata Orchestration:** Manage the state and relationship between raw file data and its digital twin in the metadata layer, ensuring that relational and semantic data remain in sync as the studio library evolves* **Context Feature Enablement:** Enable \"smart\" features within existing storage such as auto-tagging, similarity search, and automated summarizing* **On-call:** Ability to participate in an on-call rotation for critical issues **QUALIFICATIONS:** * **Full-Stack Storage Expertise:** Ability to bridge the gap between the data center and the AI agent. You leverage your background in architecting, managing, and troubleshooting physical and/or virtual storage solutions to inform how agentic workflows and metadata pipelines access underlying data at petabyte scale* **Broad Protocol Knowledge:** Expertise in how data is accessed and managed across **NFS, SMB, and S3**. You understand the nuances of file-locking, permissions, and latency across different storage protocols* **API & Middleware Development:** Proven experience building **APIs (REST, gRPC)** and middleware that sit between raw storage and application layers* **Model Context Protocol (MCP) & AI Tooling:** Understanding of **MCP** and how to build tool-calling interfaces for LLMs* **Metadata Engineering:** Proven ability to design schemas and indexing pipelines using **Kafka, ElasticSearch, or Vector DBs** to represent physical files as semantic entities* **3+ Years of Software-Driven Infrastructure:** Recent experience in scale environments where you've transitioned manual workflows into programmatic, API-driven services* **The Translator Mindset:** Ability to translate abstract creative needs (e.g., *\"I need to see all iterations of this scene\"*) into technical metadata queries that return precise results* **Versatile Backend Development:** High degree of comfort working across various programming languages to build the foundational \"glue\" that connects storage metrics and file data to agentic frameworks; deep proficiency in Python is a significant plus **PREFERRED SKILLS:** * **Modern AI Frameworks:** Hands-on experience with agentic libraries, with a focus on building custom data connectors and Retrieval-Augmented Generation (RAG) architectures* **Containerization & Orchestration:** Experience with Docker and Kubernetes for scaling metadata extraction and embedding workers* **HPC Awareness:** Understanding of the performance characteristics of high-end storage (Vast, NetApp, StorageGrid, AWS) and how to minimize the overhead of metadata operations* **Creative Pipeline Interest:** A passion for digital content creation and an interest in how AI can accelerate and modernize production workflowsThe hiring range for this position in Emeryville is $182,835.00 to $236,610.00 per year. The base pay actually offered will take into account internal equity and also may vary depending on the candidate’s geographic region, job-related knowledge, skills, and experience among other factors.Pixar is an Equal Opportunity Employer. We know our storytelling is at its best when we include, celebrate and embrace difference. We strive to be a diverse workforce that is representative of our audiences, and where all can thrive and belong. We are committed to building a team that includes and respects a variety of voices, identities, backgrounds, experiences and perspectives. Pixar participates in E-Verify and will provide the federal government with your Form I-9 information to confirm that you are authorized to work in the U.S.