Sr Backend Engineer - AI

In this role, you will design and build scalable backend systems that power AI-driven observability products, ensuring reliability, performance, and seamless integration between LLM systems and distributed infrastructure.

• Design and develop backend services powering AI agents, orchestration layers, and tool execution frameworks
• Build and maintain APIs and systems for real-time streaming of observability data (logs, metrics, traces)
• Develop MCP server capabilities enabling LLMs and agents to query and act on system data
• Architect and implement scalable distributed systems with strong focus on performance and reliability
• Work on long-running processes, session management, and stateful AI workflows across backend services
• Implement secure, production-grade systems for LLM tool-calling, evaluation, and prompt execution
• Collaborate on LLM/GenAI observability features to monitor AI-native applications using OpenTelemetry
• Drive end-to-end ownership of features from design and architecture through deployment and scaling
• Contribute to system design discussions, technical documentation, and engineering best practices

Requirements

The ideal candidate brings strong backend engineering expertise combined with hands-on experience building and shipping AI/LLM-powered systems in production environments.

• 5–8 years of experience in backend engineering building production-grade distributed systems
• Strong proficiency in Go (concurrency, performance, system design) and Python (FastAPI, asyncio, Pydantic)
• Hands-on experience building and shipping LLM/AI features such as agents, tool calling, or RAG systems
• Strong understanding of API design, data modeling, and scalable backend architectures
• Experience with asynchronous systems, streaming architectures, and event-driven design
• Ability to build reliable systems on top of non-deterministic AI/LLM behavior
• Strong ownership mindset with ability to drive projects end-to-end independently
• Excellent communication skills and ability to document and explain technical decisions clearly
• Experience in remote-first, fast-paced engineering environments
• Familiarity with observability systems or distributed tracing is a plus

Benefits

• Remote-first and async-friendly work culture
• Opportunity to build cutting-edge AI-native infrastructure products
• High-impact role shaping a new category: agent-native observability
• Work on a globally adopted open-source platform
• Highly technical, product-focused engineering environment
• Strong ownership and autonomy across the full development lifecycle
• Collaboration with a world-class engineering team shipping at high velocity
• Opportunity to contribute to widely used developer infrastructure tools.