AI Backend Engineer

Role Overview

We’re looking for an AI Engineer to design, build, and scale the core systems powering our agentic platform, translating advanced AI techniques into robust, production-grade applications.

You’ll work across the stack: from backend infrastructure and APIs to AI model integration, orchestration, and deployment. The ideal candidate thrives on building high-quality systems end-to-end, and has hands-on experience bringing AI-powered products into real-world use.

What You’ll Do

• Design, implement, and maintain production systems that integrate LLMs, retrieval-augmented generation (RAG), and tool-using agents.
• Develop the infrastructure for deploying, monitoring, and scaling AI services, ensuring reliability and performance.
• Work closely with the team across research and product to turn prototypes into robust, production-ready systems.
• Play a pivotal role in shaping how we build - technically, operationally, and culturally - as part of an early-stage team.

What You Bring

• 4+ years of professional software engineering experience, with at least 2 years working on AI-powered systems.
• Proficiency in Python and strong backend engineering skills (experience with additional languages like NodeJS, Go, or Java is a plus)
• Experience with deploying AI/ML models to production (e.g. hosting LLMs, integrating APIs, building RAG-based systems).
• Familiarity with modern full-stack development practices, cloud platforms, and containerization (Docker/Kubernetes).
• Strong understanding of distributed systems, data pipelines, and system reliability.

Bonus points if you also have:

• Experience with agent frameworks (LangGraph, Smolagents, or similar).
• Prior work on developer tools, code intelligence, or AI-driven software systems.
• Exposure to MLOps practices (CI/CD for ML, model monitoring, evaluation pipelines).
• Frontend experience (React, Next.js, or similar) to contribute across the full stack.