Agent Platform Engineer

Описание

AI is changing how every team at Similarweb works, and this role is about building a single, company-wide AI platform that everyone builds on. As an AI Engineer on the AI Platform team, you will build the foundation: the agent runtime, the tool and data layer, the model gateway, and the evaluation and observability infrastructure that turn AI experiments into reliable production systems. Your work will let Similarwebbers ship agents and AI-powered workflows in days rather than quarters.

Responsibilities

• Design and build the core agent platform — runtime, orchestration, state and memory management, and a shared agent SDK that teams across the company use instead of rebuilding foundations
• Build and operate the tool and connector layer, including MCP servers that expose Similarweb data, internal systems, and third-party services to agents in a consistent, safe way
• Develop LLM-based agents for high-value internal workflows, and turn the reusable parts of each one back into platform capabilities
• Implement integrations that let agents take automated actions on behalf of users, streamlining workflows and reducing manual overhead
• Establish secure-by-default patterns: permissioning and data-access boundaries, PII handling, prompt injection defenses, and audit logging, in line with Similarweb’s security and privacy standards
• Continuously evaluate and improve the performance of AI models and agents to ensure high-quality, data driven results

Requirements

• 5+ years of experience in software engineering, with strong proficiency in Python
• Hands-on experience with LangGraph, LangChain, or similar frameworks for building AI agents
• Strong understanding of LLMs, prompt engineering, and AI agent architectures
• Solid grounding in production engineering: REST APIs, asynchronous services, integrating external data sources, containers, and CI/CD
• Strong collaboration and communication skills, including with non-engineering stakeholders across the business

Nice to have

• Familiarity with the AI Agents ecosystem, including different LLM providers, vector store solutions, MCPs, and more
• Experience with evaluating LLM performance and quality, and with LLM observability tooling
• LLMOps experience: cost and latency optimization, semantic caching, model routing, and capacity planning
• Experience designing RAG systems over large or heterogeneous data sources
• Awareness of AI-specific security and safety concerns, and how to mitigate them in a multi-tenant internal platform
• Familiarity with cloud environments, especially AWS, and with Kubernetes and infrastructure-as-code

We offer

• Our best work is a product of our face-to-face collaboration, with the ability to work partially from home
• Competitive perks & benefits
• Regular team outings and happy hours
• Career Week, personalized coaching, and ongoing learning solutions