Back
Remote mid-level LLM role with broad popular skillset increases applicant density.
ML/LLM skills transfer across industries, though EV domain knowledge is optional.
Explicit 4–6 years plus mandatory LLM frameworks and FastAPI increases filtering.
Login to See Your Match Score
Create a free account or log in to unlock your CV match score across:
Design, develop, and optimize the backend services powering a conversational AI platform for EV fleet data using LLM and retrieval-augmented generation.
Integrate chatbot backend with existing frontend, supporting diverse fleet analytics including diagnostics, predictive insights, and performance metrics.
Evaluate and improve retrieval accuracy, latency, hallucination rates, and maintain system documentation and lifecycle management.
4-6 years of hands-on experience in Machine Learning with practical experience building LLM or Generative AI applications using LangChain, LlamaIndex, or similar.
Proficiency in Python and FastAPI, experience with retrieval pipelines and databases such as SQL, CrateDB, PostgreSQL, and vector databases like FAISS, Chroma, or Pinecone.
Ability to design efficient prompting strategies and retrieval pipelines for structured and unstructured data.
Work Experience Required: 4-6 years; Location: Candidates outside India can apply (remote).
Experienced in production-grade LLM application development with operational ownership of backend AI services in real-time analytics environments.
Familiar with EV domain analytics, fleet management data, or IoT data, enhancing the product's relevance and accuracy.
Skilled at optimizing embedding techniques, managing AI hallucinations, and implementing AI orchestration frameworks to improve system performance and reliability.