AI Engineer

About the role

You will own the end-to-end delivery of the Apify MCP Server, turning tens of thousands of Actors into reliable tools that autonomous agents can call with confidence. You will own the design and evolution of the runtime that powers Apify AI, shaping how agents discover, call, and pay for tools in a rapidly changing protocol landscape. You will build the evals that convert real production traces into automated tests, closing the loop between deployment and measurable product quality. You will own the implementation of critical integrations like dynamic tool discovery and agentic payments aligned with Coinbase's x402 standard. You will own the hard problems around stateless transports, authorization hardening, and tool discovery that keep the platform secure and scalable. You will own the interface between the platform and agents, ensuring natural language remains a first-class interaction model. You will partner closely with product and infrastructure to iterate quickly and ship features that define how agents interact with web-scale data.

Key facts

What you'll do

• Build and maintain the Apify MCP Server, turning tens of thousands of Actors into tools that agents can reliably call.
• Keep the server ahead of a protocol that changes fast and often breaks: stateless transports, authorization hardening, and tool discovery.
• Shape the agent behind Apify AI, from the runtime it runs on to the tools it reaches and the rough edges that surface when it runs a full task end-to-end.
• Help autonomous agents discover and pay for Apify tools, integrating capabilities such as Coinbase x402 where relevant.
• Build evals that turn real production traces into tests, catch regressions in CI, and tell us whether a change made the product better or worse.
• Own the end-to-end reliability of tool calling flows, ensuring agents can depend on Apify Actors under load and failure.
• Collaborate with frontend and infrastructure teams to align the MCP layer with the broader product vision and runtime constraints.
• Instrument and observe the platform in production, using data to drive improvements in performance and developer experience.
• Contribute to the design of the agentic economy, including dynamic discovery, routing, and payment mechanisms.
• Translate messy real-world usage patterns into robust abstractions that keep the platform simple and predictable.
• Partner with security and platform teams to harden integrations and reduce the attack surface of tool calling.
• Define and maintain the contract between large language models and the Apify platform through schemas and protocols.
• Prioritize work in a fast-moving environment where requirements evolve weekly and shipping multiple times per day is the norm.
• Mentor and enable other engineers by sharing patterns, tooling, and learnings from production incidents.

Requirements

• 3+ years building real software, with backend experience in Node.js/TypeScript or Python.
• You have built something on top of LLMs and know the pain firsthand: tools the model calls wrong, context that balloons, agents that confidently do the wrong thing.
• You are comfortable with loosely defined problems and keeping up with a field that changes every week.
• You use the Apify platform today or want to use it and care deeply about building tools other people enjoy using.
• You communicate clearly in English, both in writing and in conversation.
• You understand the demands of production systems and care about observability, testing, and reliability.
• You are able to work full-time from our offices in Prague or remotely with valid legal documentation.
• You are self-driven and able to deliver against ambiguous requirements with minimal supervision.

Nice to have

• Experience with MCP, dynamic tool discovery, and agentic workflows.
• Contributions to open source projects related to agents, LLMs, or web automation.
• Familiarity with Coinbase x402 and agentic payment flows.
• Hands-on experience building and running infrastructure on AWS.
• Knowledge of automated testing for LLM-powered systems.
• Participation in the Apify community, including the Prague Crawl or public talks.

Practical notes

• Full-time position.
• Based in Prague (100Yards) or Brno (Titanium), with the option to work fully remotely.
• Flexible working hours to accommodate night owls and early birds.
• Two-week sprints with code reviews, tests, and frequent deployments.
• Unlimited Claude for every Apifier with no token counting.
• Open to pets, kids, and bikes in the office.
• Regular offsites and team adventures including biking, canoeing, and other activities.
• Valid legal documentation required for remote work or relocation support.