Senior Backend Engineer - AI Agents Team

Surf AI is the agentic operations platform for enterprise security teams. We don't just surface risk, we close it. Our platform connects context across identity, cloud, HR, IT, and SaaS systems, and uses specialized AI agents to drive remediation end-to-end, with human oversight at every step.

We're backed by Accel, Cyberstarts, and Boldstart Ventures, and trusted by Fortune 500 enterprises already deploying Surf in production.

Our team is small and senior, with deep roots in identity, security, and enterprise infrastructure. We work at the intersection of agentic AI and applied security - and we take seriously what it means to build systems that act in real enterprise environments.

Who are we looking for?

We're are looking for a Senior Python Backend Engineer to join the AI Agent Team, which develops agentic AI systems operating at enterprise scale. This role combines high-performance backend engineering with hands-on development of LLM-driven features and retrieval architectures. You will design, develop, and own production systems that integrate Large Language Models, embeddings, and multi-agent workflows, ensuring scalability, observability, and reliability across cloud environments.

What you'll do

• Design and develop scalable backend services for Surf AI agentic platform.
• Build production-ready retrieval and embedding pipelines integrating vector databases and LLMs.
• Implement performant, observable, and secure micro-services in a Kubernetes-based environment.
• Collaborate with data science and AI research teams to operationalize LLM and agent-based features.
• Optimize system performance, reliability, and cost for large-scale distributed workloads.
• Maintain high code quality, test coverage, and continuous deployment practices.

Required Skills & Experience

• 5+ years of backend development experience in production environments.
• Strong proficiency in Python and solid understanding of computer science fundamentals (data structures, algorithms, concurrency).
• Proven experience building large-scale distributed systems with cloud-native technologies.
• Hands-on experience with Kubernetes, Docker, and CI/CD pipelines.
• Familiarity with LangChain, LangGraph, or similar LLM frameworks.
• Experience with vector databases (e.g., Pinecone, Qdrant, Milvus, pgvector, Redis) - advantage.
• Practical understanding of LLM integration (OpenAI, Anthropic, Google Gemini, or open-source models).
• Strong communication skills, proactive ownership, and ability to deliver in a fast-paced environment.

Why Join Us?
If you want to work on foundational systems, ship AI into production, and help define how agentic security actually operates, this is an opportunity to do it early and with real ownership.