onsite
Associate AI Data Engineer - EXL Service
Data Engineer
Develop and deploy LLM‑based AI solutions, building RAG pipelines, prompt engineering workflows, and backend APIs using Python frameworks such as FastAPI, Flask, and Streamlit.
About the role
Key Responsibilities
- Design and implement large language model (LLM) applications for use cases like chatbots, summarisation, and document intelligence.
- Build and optimise Retrieval Augmented Generation (RAG) pipelines, handling data ingestion, embedding creation, and efficient retrieval.
- Apply prompt engineering techniques, including prompt design, chaining, and optimisation to improve model outputs.
- Develop robust backend services and APIs for AI applications using Python frameworks such as FastAPI, Flask, and Streamlit.
- Integrate LLM solutions with enterprise systems and both structured and unstructured data sources.
- Implement basic guardrails and evaluation methods to enhance response quality and mitigate hallucinations.
Requirements
- Proficiency in Python and experience with web frameworks (FastAPI, Flask, Streamlit).
- Hands‑on knowledge of large language models and prompt engineering.
- Experience building RAG pipelines, including data ingestion, embeddings, and retrieval mechanisms.
- Ability to design and expose APIs for AI services and integrate them with enterprise data sources.
- Strong problem‑solving skills and a focus on delivering production‑ready AI solutions.