Staff Software Engineer, Ads Agent Infra

Pinterest•San Francisco, CA

3d•$208,454 - $364,795•Hybrid

About The Position

As a Staff Software Engineer on Pinterest’s Ads Agent Infrastructure team, you’ll build and scale the foundation powering Pinterest’s stateful AI agents across monetization and advertiser platforms. You’ll drive the technical direction for distributed agent architectures, memory services, and execution engines that enable engineering teams across Pinterest to deploy resilient agentic workflows. The role involves architecting durable execution platforms for crash-recoverable, stateful AI agent workflows; creating standardized Model Context Protocol (MCP) servers, SDKs, and agent runtime interfaces; and establishing observability, execution tracing, prompt versioning, and token-based cost governance for multi-agent systems. You’ll also set technical strategy, write foundational design documents, and work across infrastructure, security, and product teams. AI is used to accelerate prototyping, documentation, and code iteration, with a focus on verifying the quality and correctness of AI-assisted work. The role requires being within commuting distance of Pinterest’s San Francisco or Palo Alto office for in-person collaboration 1–2 times each quarter. It is not eligible for relocation assistance. The position is eligible for equity. The posted US base salary range is $208,454–$364,795.

Requirements

At least 8 years of software engineering experience, with expertise in distributed systems, microservices, and durable execution engines such as Restate, Temporal, or Step Functions.
Hands-on experience with LLM agent frameworks and runtime internals, including LangGraph, DeepAgents, or Claude Agent SDK.
Expertise in setting technical direction for platform abstractions and driving cross-functional alignment across infrastructure, security, and product teams.
Experience with service identity, multi-tenant security (mTLS, SPIFFE), and LLM observability or cost governance frameworks.
Demonstrated ability to use AI to improve the speed and quality of day-to-day work for relevant outputs.
Strong track record of critically evaluating and verifying AI-assisted work, including testing, source-checking, and peer code review.
High integrity and ownership, including protecting sensitive data, avoiding over-reliance on AI, and remaining accountable for final decisions and deliverables.
Bachelor’s or Master’s degree in Computer Science, a related field, or equivalent experience.

Responsibilities

Architect, build, and maintain durable execution platforms supporting crash-recoverable, stateful AI agent workflows.
Design standardized Model Context Protocol (MCP) servers, SDKs, and agent runtime interfaces for adoption by engineering teams across the company.
Establish LLM observability, execution tracing, prompt versioning, and token-based cost governance across multi-agent systems.
Drive technical strategy and write foundational design documents that align infrastructure, security, and product teams.
Use AI to accelerate design prototyping, documentation, and code iteration while applying judgment and verification to ensure correctness and quality.
Automate repeatable testing, evaluation, and grader pipelines for agent skills and memory services.