Staff Engineer, Applied AI

AI at Zapier

At Zapier, we leverage automation daily to enhance work efficiency, creativity, and human focus. We encourage the responsible and transparent use of AI tools during your application process, providing clear guidance on how to collaborate with AI during Zapier’s Hiring Process, including tools like ChatGPT, Claude, and Gemini.

About Zapier

Zapier is a platform empowering millions of businesses through automation and AI. Our mission is to make automation accessible to everyone. Joining our team means collaborating with intelligent, curious individuals, building cutting-edge tools, and benefiting from flexible remote work. Your contributions will directly drive customer success and foster your personal growth.

• Culture and Values at Zapier
• Zapier Guide to Remote Work
• Zapier Code of Conduct
• Diversity and Inclusivity at Zapier

About The Role: Staff Engineer, Applied AI

Zapier is seeking a Staff Engineer, Applied AI for its AI Capabilities team. This team is responsible for developing the shared AI execution platform that powers all of Zapier's AI products, including Agents, Chatbots, AI by Zapier, and future orchestration experiences. This is considered one of the most foundational engineering roles at Zapier today.

The AI Capabilities team is focused on unifying runtimes, tooling, data models, and orchestration layers across our AI products into a single, reliable, high-quality platform with excellent ergonomics. We are building the essential AI foundation for Zapier, accelerating the work of all other AI teams.

As a Staff Engineer, Applied AI, you will bring deep technical expertise in LLMs, orchestration, evaluation, runtime systems, and platform engineering. You will play a crucial role in shaping our unified architecture, guiding critical trade-offs, elevating engineering standards, and ensuring the platform is scalable, secure, cost-efficient, and easy to build upon.

This role is ideal for those passionate about solving complex AI platform problems that directly impact user-facing products and who are energized by building a foundation relied upon by AI-focused teams and millions of users.

Why this is different (and exciting)

This unique opportunity allows you to contribute to the AI platform behind one of the world’s largest automation ecosystems. The AI Capabilities team supports every runtime AI product at Zapier, including Agents, Chatbots, AI by Zapier, and upcoming orchestration surfaces.

You will tackle significant challenges: making AI reliable, fast, safe, cost-efficient, and user-friendly. Your work will empower product teams to launch smarter features more quickly, with your impact directly visible in the customer experiences that drive their businesses.

If you are excited by high-leverage engineering work combining platform design, system architecture, and applied AI, this role offers a front-row seat to shape the future of intelligent automation at scale.

About You

• Proven engineering impact: Demonstrated success driving outcomes in complex, cloud-based systems used by real customers. Experience securing or expanding enterprise deals (POCs, security/compliance, product requirements) is a bonus. Many Staff-level candidates have 10+ years of experience, though Zapier prioritizes impact and capability.
• LLM expertise: At least 2 years of hands-on experience with large language models in production, including user-facing products leveraging agent architectures. Familiarity with transformer networks, attention mechanisms, and their role in generating responses and function calls.
• Evaluation & retrieval systems: Direct experience deploying LLM evaluation frameworks (performance, reliability, bias) and building Retrieval-Augmented Generation (RAG) systems. Nuanced understanding of indexing/chunking strategies, semantic search, and vector databases, and their differentiation from traditional retrieval.
• Builder first: Leads through hands-on contributions, partnering with product teams, unblocking adoption, modeling best practices, and shipping code.
• Pragmatic judgment over novelty: Ability to distinguish signal from hype. Comfortable deeming technology "not ready for production" and explaining why. Partners with product to decide between exploration, standardization, and scaling, based on evaluations, user impact, and cost/latency trade-offs.
• Designs for scale and ambiguity: Capable of designing robust systems and solutions in complex, high-scale environments with fluid priorities and inherent ambiguity.
• Skilled communicator: Excels in pair programming, cross-functional problem-solving, and customer discovery. Evaluates solutions based on speed to impact and customer experience cohesion. Builds trusting relationships and influences others.
• AI power user: Proactively integrates AI into engineering workflows, actively exploring new ways to accelerate learning, development, and operations. Advocates for AI, sharing workflows and helping colleagues grow their AI skills.

Things You’ll Do

• Lead key architectural efforts for Zapier's unified AI platform, defining orchestrator architecture, shared runtime components, and foundational APIs for various AI experiences.
• Guide high-impact technical decisions across AI Capabilities, influencing orchestration patterns, execution flows, shared tools, memory management, safety, and data model design.
• Provide technical oversight during the consolidation of multiple runtimes into a single orchestrator, balancing reliability, speed, safety, and developer ergonomics.
• Partner extensively with product teams across the AI organization (Agents, Chatbots, AI Tasks, Copilot, Chat) to support migrations, define interfaces, and translate product needs into platform capabilities.
• Mentor engineers and elevate the technical standards within AI Capabilities, sharing patterns, teaching practical AI engineering, and fostering a strong platform engineering culture.

Work Hours & Collaboration Expectations

This is a globally remote role. However, due to the concentration of stakeholders and partner teams in North America, this role requires working standard Eastern Time (ET) hours at least three days per week for real-time collaboration and decision-making. Outside these days, you can set your own hours, ensuring they meet team needs and comply with local regulations.

Key skills/competency

• Large Language Models (LLMs)
• AI Orchestration
• Platform Engineering
• System Architecture
• Retrieval-Augmented Generation (RAG)
• Vector Databases
• Evaluation Frameworks
• Cloud-based Systems
• API Design
• Technical Leadership