LLM Platform Engineer/Lead (m/f/d)

Key details

Full job description

Kayzen is seeking an LLM Platform Engineer/Lead to join the Engineering team remotely from EMEA or Bangalore. The role involves building internal AI frameworks, SDKs, and shared libraries to enable teams to integrate AI features quickly and safely. Responsibilities include designing reusable AI components, setting best practices for AI usage and cost control, evangelising AI internally, and owning AI tooling from experimentation to production. Candidates must have hands-on experience with LLM APIs (OpenAI, Anthropic), RAG pipelines, embeddings, vector databases, prompt engineering, AI orchestration frameworks, and strong Python skills. Experience with cloud platforms (AWS, GCP, Azure), Docker, and CI/CD is desirable. The role requires shipping LLM-powered features to production and iterating based on feedback. The position offers flexible remote work, direct reporting to the CTO, career growth, a multinational team, and budgets for home office setup and learning.