AI Engineer (Python, LLMs & RAG)

Role Overview
We are looking for an AI Engineer to build generative AI features that integrate with existing products and perform reliably in production.

Key Responsibilities

• Develop Python applications and services that interact with large language models (LLMs) through APIs.
• Build retrieval-augmented generation (RAG) workflows, including document preparation, embeddings, information retrieval, and response evaluation.
• Integrate AI features with existing APIs and services.
• Monitor solution quality, latency, cost, and performance in production.
• Collaborate with engineering and product teams to turn use cases into working features.

Required Qualifications

• Professional software development experience with Python.
• Hands-on experience building solutions with LLMs and RAG.
• Experience developing and integrating APIs, with sound testing and deployment practices.
• Ability to clearly explain your individual contributions and how you evaluated the results.

Nice to Have

• Experience with LangChain or LlamaIndex.
• Experience with vector databases, cloud platforms, or observability tools.