Data Scientist / AI Engineer (Python, ML, RAG)

Roles & ResponsibilitiesDesign and develop intelligent AI-based applications using advanced NLP and LLM techniques to solve real-world business challenges in financial services. Build and optimize Retrieval-Augmented Generation (RAG) pipelines leveraging structured and unstructured financial data. Integrate and orchestrate LLMs/SLMs for question-answering, summarization, semantic search, and document understanding. Develop and maintain RESTful APIs (sync and async) to serve NLP models and chatbot interfaces using frameworks like FastAPI, Flask, etc. Should have knowledge of advanced prompting techniques. Implement semantic search, hybrid search, and text retrieval systems using Elasticsearch and vector databases (e.g., FAISS, Pinecone, Weaviate). Perform NLP tasks such as entity recognition, text classification, intent detection, embedding generation, and sentiment analysis where required. Monitor and fine-tune LLM/SLM performance with real-world user data to improve relevance, latency, and accuracy. Exposure to LLMOps tools for monitoring, evaluation, and versioning of AI models in production. Build, train, and evaluate deep learning models for NLP tasks including classification, NER, summarization, and embedding generation. Develop traditional machine learning models (e.g., regression, decision trees, clustering) for structured data analysis and prediction tasks. Interact with cross-functional teams to understand system issues and follow up with respective teams to get them fixed. Understand and identify areas of improvement across businesses and participate in solution identification and implementation. Should be able to work as an Individual Contributor on new and existing projects. Positive and problem-solving attitude, must work as an independent contributor. Skills: nlp,data,classification,advanced,models,semantic search