Senior AI Engineer

You will build and scale the next generation of AI-driven products at Atari, bridging the gap between data science and product engineering. You'll design and implement scalable architectures for both front-end interfaces and back-end microservices, build and secure APIs, and configure data models to support AI workloads. You will integrate Large Language Models and machine learning artifacts into production, focusing on latency, reliability, and cost efficiency. You'll lead the design of Retrieval-Augmented Generation systems, handling data chunking, embedding, indexing, and retrieval, and you'll optimize AI application performance through prompt engineering, caching, and inference tuning, all while collaborating closely with Data Scientists and MLOps Engineers.

Responsibilities

• Design and implement scalable, high-performance architectures for front-end interfaces and back-end microservices
• Build, document, and secure efficient RESTful or GraphQL APIs to enable data and model communication
• Configure and optimize data models in relational and non-relational Vector Databases to support AI workloads
• Develop unit, integration, and end-to-end tests and manage deployment pipelines
• Integrate Large Language Models and machine learning artifacts into production environments
• Lead the design and development of Retrieval-Augmented Generation systems
• Manage data chunking, embedding, indexing, and retrieval for contextual responses
• Improve AI application responsiveness via prompt engineering, caching, and inference optimization
• Work closely with Data Scientists and MLOps Engineers to deploy, monitor, and continuously improve AI systems in production

Requirements

• 5+ years of experience as a Full Stack Software Engineer, including at least 1 year of hands-on AI/ML integration experience
• Strong front-end development skills in TypeScript/JavaScript and frameworks like React or Next.js
• Advanced back-end development experience in Python (preferred) or Node.js, with proven ability to build scalable APIs
• Proficiency with LLM APIs (OpenAI, Gemini, Claude), frameworks like LangChain or LlamaIndex, and hands-on experience with Claude Code and Model Context Protocol (MCP)
• Experience with containerization (Docker) and deployment on major cloud platforms (AWS, GCP)