Senior AI/LLM Engineer (Python) – Remote

About the role

Kake is looking for a Senior AI/LLM Engineer with strong Python expertise to design, build, and productionize large‑language‑model‑powered applications. You will work remotely, collaborating with a global community of senior engineers to deliver AI features at scale.

Key responsibilities

• Design, develop, and deploy LLM‑powered features and applications using Python and FastAPI.
• Build and optimise Retrieval‑Augmented Generation (RAG) pipelines, including embeddings, vector search and retrieval strategies.
• Create, test and iterate prompts, agents and orchestration flows with frameworks such as LangChain or LlamaIndex.
• Integrate with LLM providers (OpenAI, Anthropic, open‑source models) while managing cost, latency and quality trade‑offs.
• Develop tooling and metrics to evaluate model output for accuracy, safety and regression.
• Maintain containerised environments and data infrastructure (Docker, PostgreSQL, Redis, vector databases) for reliable production AI systems.

Required profile

• Strong proficiency in Python and experience with FastAPI or similar backend frameworks.
• Hands‑on experience with LLM APIs and frameworks such as LangChain or LlamaIndex.
• Experience building RAG architectures and working with vector databases (e.g., Pinecone, Weaviate, pgvector).
• Proficiency with Docker, PostgreSQL, Redis and writing functional/integration tests.
• Excellent written and verbal communication in English and ability to work independently in a remote, fast‑paced environment.

Required skills

• Python
• FastAPI
• LangChain
• LlamaIndex
• OpenAI / Anthropic APIs
• Vector databases (Pinecone, Weaviate, pgvector)
• Docker
• PostgreSQL
• Redis
• Functional and integration testing

What we offer

• Competitive USD salary paid globally.
• Fully remote work environment.
• Better Me Fund for personal growth and passions.
• Community focused on social good and professional development.