Responsibilities:

- Research, design, and develop ML models for metadata extraction, information retrieval, and RAG applications.

- Define AI architecture, tools, and Azure integrations, optimizing cloud-based model deployment.

- Implement schema retrieval pipelines using embeddings, FAISS/VectorDB, and ranking mechanisms.

- Develop pipelines for data preprocessing, metadata structuring, and structured query generation.

- Apply MLOps principles for scalable, automated AI/ML workflows.

- Enhance bot interactions with natural language processing, improving accuracy and reducing hallucinations.

- Deploy AI models and APIs on Azure, optimizing performance and cost.

- Perform testing for functional, integration, and load scenarios, ensuring query accuracy.

- Collaborate with cross-functional teams to define requirements and drive AI solutions.

Must Have Skills:

- 6+ years in AI/ML, NLP, Python,



with a robust focus on Azure.
-

- Expertise in RAG, NLP, Computer Vision, schema retrieval, and deep learning.

- Experience with FAISS/Vector DB, SQL, data preprocessing, and database integration in OneLake.

- Hands-on deployment and optimization of AI-powered bots and LLMs.

- Proficiency in microservices, Docker, and Kubernetes (Azure Kubernetes Service preferred).

- Strong MLOps practices, including CI/CD, monitoring, and lifecycle automation.

- Ability to optimize AI models for performance and efficiency in production.

- Strong Python skills with TensorFlow, PyTorch, LangChain, and FAISS.
-

- Excellent communication skills for technical and non-technical audiences

📌 Technical Lead Data Scientist (Gurugram)
🏢 Srijan
📍 Gurugram