Staff Engineer, Applied AI

Zapier•San Francisco, CA

19d•Remote

About The Position

Zapier is hiring a Staff Applied AI Engineer for our AI Capabilities team, the group responsible for building the shared AI execution platform that powers every AI product at Zapier, including Agents, Chatbots, AI by Zapier, and future orchestration experiences. This is one of the most foundational engineering roles at Zapier today. AI Capabilities is unifying the runtimes, tooling, data models, and orchestration layers behind our AI products into a single, reliable, high-quality platform with great ergonomics. We’re building what Zapier’s AI foundation should have been from day one—and we’re delivering it in a way that accelerates all other AI teams. As the Staff Applied AI Engineer on this team, you’ll bring deep technical expertise in LLMs, orchestration, evaluation, runtime systems, and platform engineering. You’ll help shape our unified architecture, guide tough tradeoffs, elevate our engineering standards, and ensure the platform is scalable, safe, cost-efficient, and easy to build on. If you want to work on hard AI platform problems that directly impact user-facing products—and you’re energized by building the foundation that other AI-focused teams and millions of users will rely on—you’ll thrive here. Why this is different (and exciting) This is a rare opportunity to help build the AI platform behind one of the world’s largest automation ecosystems. The AI Capabilities team empowers every runtime AI product at Zapier; Agents, Chatbots, AI by Zapier, and the orchestration surfaces yet to come. You’ll work on challenges that matter: making AI reliable, fast, safe, cost-efficient, and easy to build on. Your work will enable product teams to ship smarter features faster, and you’ll see your impact reflected directly in the experiences our customers use to run their businesses. If you’re excited about high-leverage engineering work that blends platform design, system architecture, and applied AI, this role gives you a front-row seat to shape how intelligent automation gets built at scale.

Requirements

Proven engineering impact: You’ve driven outcomes in complex, cloud-based systems used by real customers. Bonus: you’ve helped win or expand enterprise deals—leading POCs, navigating security/compliance reviews, or shaping product requirements to land enterprise adoption. Many strong candidates for our Staff roles have 10+ years’ experience. We hire for impact and capability, not years.
LLM expertise: You have at least 2 years or equivalent depth of hands-on work with large language models in production, including user-facing products leveraging agent architectures. You are familiar with transformer networks, attention mechanisms, and their role in generating responses, function calls, and other complex tasks.
Evaluation & retrieval systems: You have direct experience deploying evaluation frameworks for LLMs (performance, reliability, bias) and building Retrieval-Augmented Generation (RAG) systems. You have nuanced perspectives and experience with indexing/chunking strategies, semantic search, and vector databases, and how they differ from traditional retrieval methods.
Builder first: You lead through hands-on contribution—pairing with product teams, unblocking adoption, modeling best practices, and shipping. You execute, not just advise.
Pragmatic judgment over novelty: You separate signal from hype. You’re comfortable saying “not ready for production” (and explaining why), and you partner with product to decide when to keep exploring vs. when to lock down, standardize, and scale—using results from evals, user impact, and clear cost/latency tradeoffs.
You design for scale and ambiguity. You can design systems and solutions in complex, high-scale environments—where priorities are fluid and ambiguity is the norm.
Skilled communicator: You’re known for moving fluidly between pair programming, cross functional problem-solving, and customer discovery. You evaluate long vs. short-term solutions through the lens of speed to impact and cohesion of customer experience. You form trusting relationships and know how to bring others with you.
You are an AI power user. You proactively embrace AI as a core part of your engineering toolkit and are excited to explore new ways it can accelerate learning, development, and operations. You don’t just use AI—you advocate for it, sharing your workflows and helping others level up.

Responsibilities

Lead key architectural efforts in our unified AI platform: You’ll help define the orchestrator architecture, shared runtime components, and foundational APIs that bring Chatbots, Agents, AI by Zapier, and future experiences onto one high-quality platform.
Guide high-impact technical decisions across AI Capabilities: You’ll influence choices around orchestration patterns, execution flows, shared tools, memory, safety, and data model design.
Provide technical oversight as we consolidate runtimes: You’ll help navigate the merging of multiple systems into a single orchestrator; balancing reliability, speed, safety, and developer ergonomics.
Partner deeply with product teams across the AI org: You’ll work closely with Agents, Chatbots, AI Tasks, Copilot, and Chat surfaces to support migrations, define interfaces, and translate product needs into platform capabilities.
Mentor engineers and raise the technical bar for AI Capabilities: You’ll share patterns, teach practical AI engineering, and help grow the platform engineering culture on the teams you work with.

Stand Out From the Crowd

Upload your resume and get instant feedback on how well it matches this job.

Upload and Match Resume