Job Description

Roles & Responsibilities

• Design and develop AI-driven applications leveraging LLMs (OpenAI, Hugging Face models, or local LLMs)

• Build and optimize workflows using frameworks like LangChain, LlamaIndex, or Haystack

• Engineer effective prompts for various use cases, ensuring accuracy and consistency

• Integrate text-to-SQL models to convert natural language queries into database operations

• Work with vector databases (FAISS, Chroma, Pinecone) for semantic search and retrieval tasks

• Implement document processing pipelines including PDF ingestion, text chunking, and embedding generation

• Generate interactive data visualizations using Plotly, Vega-lite, or JSON-based charting tools

• Collaborate with data engineers, analysts, and product teams to deliver robust AI solutions

• Maintain clean, modular, and scalable Python code

Desired Candidate Profile

• Strong experience with LLM frameworks (e.g., LangChain, LlamaIndex, Haystack)

• Familiarity with LLM APIs such as OpenAI, Cohere, or local models via Hugging Face

• Hands-on experience with prompt engineering and model fine-tuning (preferred)

• Proficiency in vector databases: FAISS, Pinecone, or Chroma

• Solid understanding of document processing: text chunking, embedding strategies, and retrieval pipelines

• Knowledge of text-to-SQL model integration and query optimization

• Experience with data visualization tools: Plotly, Vega-lite, or equivalent

• Strong command of SQL and Python

• Excellent problem-solving skills and ability to work in a fast-paced environment