AI Engineer - AI Agents Team

Surf AI is building the world’s first context-driven, agentic security platform. We focus on systems that don’t just surface risk, but actively help organizations resolve it.

Surf is backed by Cyberstarts and Boldstart Ventures, investors behind category-defining security companies, and founded by repeat entrepreneurs with deep experience in identity, security, and enterprise risk.

We’re a small, senior team working at the intersection of security, AI, and distributed systems. Our work blends agentic systems with data-driven analysis and applied security research to operate safely in real enterprise environments.

Who are we looking for?

We're looking for an AI Engineer to design, build, and scale production-grade AI systems powered by Large Language Models (LLMs) and autonomous agents.
You’ll bridge research and engineering—turning cutting-edge models into reliable, observable, and high-impact product features.
This role is ideal for engineers who love combining deep technical work with real product impact, collaborating closely with data scientists, backend engineers, and product teams.

What you'll do

• Develop and deploy LLM-based systems and AI agents that interact with data sources, APIs, and user interfaces.
• Implement retrieval-augmented generation (RAG), fine-tuning, and prompt-optimization workflows for specific product domains.
• Build and maintain the infrastructure for agent orchestration, evaluation, and lifecycle management.
• Collaborate with Data Science to integrate models into production pipelines with strong reliability, monitoring, and observability.
• Contribute to internal frameworks for tool-use, memory, and multi-agent coordination.

Required Skills & Experience

• 5+ years of experience in software engineering, machine learning, or AI systems development.
• Strong programming skills in Python and hands-on experience with LangChain, LangGraph, or similar frameworks.
• Proven experience integrating LLMs (OpenAI, Anthropic, local models) into production applications.
• Proficiency with PyTorch, Hugging Face, or other model-serving ecosystems.
• Familiarity with containerized deployments (Docker, Kubernetes) and cloud-native development (AWS, GCP, or Azure).
• Understanding of retrieval, embeddings, and vector databases (pgvector, Pinecone, Weaviate).
• Strong system design skills and experience building robust APIs or services around ML components.

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.