Senior Backend Engineer - AI platform

Job description

*At Similarweb, we are revolutionizing the way businesses interact with the digital world by revealing to them everything that happens online.* *Our unique data and solutions empower thousands of customers globally, including industry giants like Google, eBay, and Adidas, to make game-changing decisions that drive their digital strategies.* *In 2021, we went public on the New York Stock Exchange, and we continue to reach new heights! Come work alongside Similarwebbers across the globe who are bright, curious, practical, and good people.* **Why is this role so important at Similarweb?** AI is transforming how Similarweb operates, but scaling it requires a robust, production-grade foundation. Instead of every product and internal engineering team reinventing infrastructure, we are building a centralized, high-throughput AI Platform. As a **Senior Backend Engineer (AI Platform),** you will design and implement the resilient core services powering our AI ecosystem: high-concurrency agent runtimes, distributed tool and data pipelines, low-latency model gateways, and real-time evaluation and observability systems. Your internal customers are teams across the whole company, including engineers, data scientists, back office and product teams - your systems will turn AI prototypes into scalable, fault-tolerant production services deployed across Similarweb. You will not build isolated AI features; you will build the scalable platform layer that handles state management, routing, and system reliability for dozens of high-throughput AI workflows. **What will you be doing?** - **Core Systems Design:** Architect and build the high-availability agent platform - focusing on distributed orchestration, state/memory persistence layer performance, event-driven execution, and a high-performance Python SDK. - **API & Integration Architecture:** Design and operate scalable tool and connector services, including standardized Model Context Protocol (MCP) servers, gRPC/REST endpoints, and secure wrappers for Similarweb data stores, internal microservices, and external APIs. - **Low-Latency Model Infrastructure:** Build low-latency model gateways, connection pooling, automated failover routing, semantic caching layers, and rate-limiting infrastructure. - **Security & Governance:** Implement zero-trust security patterns at the platform layer: fine-grained access control (RBAC/ABAC), isolated data boundaries, PII detection pipelines, and high-throughput audit logging. - **Reliability & Performance Engineering:** Optimize distributed execution to ensure strict SLA compliance, minimizing end-to-end latency and compute costs while ensuring system observability through distributed tracing and custom metrics. **This is the perfect job for someone who brings:** - **5+ years of software engineering experience** in backend development, with advanced proficiency in Python and backend system architecture. - **Strong system design background:** Experience building asynchronous microservices, REST/gRPC APIs, distributed state management, containers, and CI/CD pipelines. - **AI Framework Engineering:** Hands-on experience building or extending agentic runtime frameworks (LangGraph, LangChain). - **Production Operations:** Solid grounding in database architecture (SQL, NoSQL, Vector Databases), caching strategies (Redis), and event-driven messaging (Kafka/RabbitMQ). - **Cross-functional Collaboration:** Proven ability to design clear API contracts and developer-facing platform tooling for other engineering teams. **Preferred Skills:** - **Infrastructure & Cloud:** Hands-on experience with AWS, Kubernetes, Terraform/CloudFormation, and modern cloud-native deployment patterns. - **LLMOps & System Optimization:** Expertise in cost and latency optimization, dynamic model routing, load balancing, and capacity planning for high-volume LLM workloads. - **Data Engineering & RAG:** Experience designing scalable retrieval-augmented generation (RAG) pipelines over large-scale, heterogeneous data lakes. - **Observability & Monitoring:** Experience setting up distributed tracing and custom APM dashboards for backend services. **Why you’ll love being a Similarwebber:** - **Impact********:** Work with the world’s leading digital intelligence platform and make a real difference. - **Innovation** ******:** Bring your ideas forward - we empower you to drive change. - **Hybrid work model**: 3 days in our office and 2 days working from home. - **Our Office:** Modern space in Prague’s DOCK IN area, stocked with snacks, drinks (we're big fans of kombucha), fruit and lunches on Tuedays. - **Benefits:** 5 weeks of vacation, birthday day off, 3 sick days, or Multisport  - **Top-tier Hardware********:** MacBook Pro M5, dual monitors, standing desks. - **Team Events********:** Regular team-building activities, monthly birthday celebrations with cakes and drinks, baking Thursdays and happy hours. - **Equity********:** Share in Similarweb’s success. - **Career Growth********:** Explore any path - leadership, switching teams, or upskilling through coaching and learning programs. We will handle your application and information related to your application in accordance with the Applicant Privacy Policy available [here](https://www.similarweb.com/corp/legal/applicant-privacy-policies/).