Machine Learning Engineer - LLM & GenAI

About Datakrew Datakrew is revolutionizing EV fleet intelligence with cutting-edge IoT/AI solutions. Our flagship solution, OXRED Platform Suite, provides deep insights into vehicle fleet performance and diagnostics. Our goal is to serve one million EVs within the next 5 years, and as a company, touch a billion lives with technology. This is a Global position and we are looking for candidates outside India. We are looking for an ML – LLM & GenAI to join our team. The ideal candidate has hands-on experience building production-grade LLM applications and will play a key role in developing AskOX, the conversational AI layer of the OXRED Platform that enables users to interact with fleet data using natural language. The role focuses on designing, building, and optimizing the LLM backend that powers this system. Key Responsibilities LLM and Backend Development Design, develop, and maintain the LLM-powered backend services using Python and FastAPI. Implement retrieval-augmented generation (RAG) to fetch structured and unstructured data from OXRED. Use frameworks like LangChain, LlamaIndex, or Haystack to manage context retrieval, query routing, and summarization. Design prompt engineering strategies, structured output generation, and intent classification pipelines. Integration and Testing Integrate the chatbot logic with the existing OXRED AskOX frontend. Design, implement, and validate support for diverse fleet analytics use cases including fleet summaries, vehicle diagnostics, predictive insights, and performance metrics. Ensure secure and efficient data flow between OXRED APIs and the AskOX backend. Optimization and Reporting Evaluate and improve retrieval accuracy, latency, and hallucination rates. Implement caching or schema-based memory for frequently accessed data. Develop automated evaluation pipelines and benchmark retrieval quality, response accuracy, latency, and hallucination rates. Documentation and Handoff Maintain technical documentation and API specifications. Document system architecture, prompt strategies, and deployment procedures. Contribute to model lifecycle management and continuous improvement. Requirements: 4–6 years of hands-on experience in Machine Learning, with demonstrated experience building LLM or Generative AI applications using LangChain, LlamaIndex, or similar frameworks. Proficiency in Python and FastAPI. Experience with retrieval pipelines, SQL, or CrateDB/PostgreSQL. Understanding of vector databases (e.g., FAISS, Chroma, Pinecone). Ability to design efficient prompting strategies and retrieval pipelines for structured and unstructured data. Knowledge in the EV Domain (brownie points). Preferred Qualifications: Knowledge of EV analytics, fleet management, or IoT data. Familiarity with OpenAI, Anthropic, or Ollama models. Experience with embedding optimization and hallucination control. Prior exposure to multi-agent or AI orchestration frameworks. Why Join Us: Work on an ecosystem of cutting-edge products combining web tech, automation, and AI. Directly influence product architecture and team growth. Engage with leading automotive and AI-driven innovation challenges. Remote working **Candidates outside India can also apply