Role Overview:

We are looking for a highly skilled and ownership-driven Data Scientist to lead and manage all AI, data processing, OCR, semantic search, and intelligent retrieval systems within our platform. This role will act as the backbone of our AI and data infrastructure, responsible for handling conversational AI workflows, document intelligence pipelines, embedding systems, and large-scale structured educational data management.

Key Responsibilities:

- Design, develop, and maintain AI-powered conversational systems and chatbot workflows.

- Manage and optimize LLM integrations including Gemini and other AI models.

- Build intelligent retrieval systems using embeddings and semantic search techniques.

- Develop and maintain OCR and document understanding pipelines using Vision-Language (VL) models.

- Work with Hugging Face-hosted inference APIs and optimize AI model usage workflows.

- Design and manage embedding generation pipelines using OpenAI embedding models.

- Develop scalable semantic search and context-aware retrieval systems.

- Handle large-scale educational datasets including colleges, courses, eligibility criteria, intakes, and institutional metadata.

- Build and maintain automated Excel-to-database synchronisation pipelines.

- Implement data cleaning, normalization, validation, and preprocessing workflows.

- Design efficient PostgreSQL database structures and optimize query performance.

- Develop intelligent matching and incremental synchronisation systems for structured datasets.

- Manage processed OCR outputs, embeddings metadata, and chatbot retrieval data.

- Improve data consistency, system scalability, and AI response accuracy.

- Collaborate closely with backend, frontend, product, and operations teams.

- Troubleshoot AI pipeline, OCR, database, and retrieval-related issues.

- Contribute to AI architecture planning, optimisation, and future scalability initiatives.