SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Similarweb is building a company-wide AI platform to standardize how AI agents and workflows are developed and deployed across the organization. Rather than having each team solve the same problems independently, this role focuses on creating the foundational infrastructure that enables dozens of AI use cases to run reliably in production.
As a Backend Engineer on the AI Platform team, you will design and build core components including the agent runtime, orchestration layer, state and memory management, and a shared agent SDK used across the company. You'll develop the tool and connector layer, including MCP servers that safely expose Similarweb data, internal systems, and third-party services to agents. Your work includes building LLM-based agents for high-value internal workflows and extracting reusable patterns back into platform capabilities.
Key responsibilities include implementing integrations that enable agents to take automated actions on behalf of users, establishing secure-by-default patterns (permissioning, data-access boundaries, PII handling, prompt injection defenses, audit logging), and continuously evaluating and improving AI model and agent performance. Your users are engineers, analysts, data scientists, and business teams across Similarweb, and your platform work enables them to ship agents and AI-powered workflows in days rather than quarters.
This is a high-leverage, horizontal role with company-wide impact. You'll set standards for how AI is built and operated at Similarweb while working in a hybrid environment that emphasizes in-office collaboration for a connected culture.
**Requirements:**
- 5+ years of software engineering experience with strong Python proficiency
- Hands-on experience with LangGraph, LangChain, or similar AI agent frameworks
- Strong understanding of LLMs, prompt engineering, and AI agent architectures
- Solid production engineering grounding: REST APIs, asynchronous services, external data integration, containers, CI/CD
- Strong collaboration and communication skills, including with non-engineering stakeholders
**Preferred Skills:**
- Familiarity with the AI Agents ecosystem (LLM providers, vector stores, MCPs)
- Experience evaluating LLM performance and quality, and with LLM observability tooling
- LLMOps experience: cost/latency optimization, semantic caching, model routing, capacity planning
- Experience designing RAG systems over large or heterogeneous data sources
- Awareness of AI-specific security and safety concerns in multi-tenant platforms
- Familiarity with cloud environments (especially AWS), Kubernetes, and infrastructure-as-code
