AI Backend Engineer

About the role

Seez is an AI‑powered automotive technology company building scalable SaaS solutions for car buying and selling. We are looking for an AI Backend Engineer who blends strong backend engineering fundamentals with modern machine‑learning expertise to create production‑ready AI applications that power the next generation of automotive retail.

Key responsibilities

• Design, develop, and maintain scalable backend services using Python, Node.js and .NET.
• Build and optimise Retrieval‑Augmented Generation (RAG) pipelines, vector‑search solutions and integrate foundation models (OpenAI, Anthropic, Gemini) into customer‑facing products.
• Create and maintain REST APIs and GraphQL endpoints that power AI services.
• Work with structured and unstructured data to improve AI performance and user experience.
• Write clean, well‑tested code, monitor system performance and continuously improve AI models in production.
• Collaborate with Product, Design and Engineering teams from concept through launch.

Required profile

• 4+ years of professional software engineering experience.
• Strong commercial background building backend applications with Python and Node.js.
• Experience developing and deploying machine‑learning or LLM‑powered applications.
• Proficiency in FastAPI or similar Python web frameworks and SQL databases such as PostgreSQL.
• Familiarity with Docker, AWS (or equivalent cloud platform) and modern CI/CD practices.
• Excellent problem‑solving abilities and strong written and verbal English communication.

Required skills

• Python
• Node.js
• .NET
• FastAPI
• REST APIs
• GraphQL
• PostgreSQL
• Docker
• AWS
• Git
• CI/CD pipelines
• LangChain (or similar orchestration frameworks)
• Vector databases (Pinecone, pgvector, Weaviate, Qdrant)
• Large Language Models (OpenAI, Anthropic, Gemini)
• Retrieval‑Augmented Generation (RAG) pipelines
• Vector search solutions