Job Description
Architect and implement RAG-based solutions integrating LLMs, embedding models, and vector databases.
2. Design and optimize semantic search pipelines using LangChain, LlamaIndex, or custom frameworks.
3. Evaluate and fine-tune LLMs for domain-specific tasks using prompt engineering and model adaptation.
4. Lead the selection, implementation, and optimization of vector databases (e.g., Pinecone, Weaviate, Milvus, PgVector).
5. Integrate vector search with traditional databases (SQL, NoSQL) for hybrid retrieval systems.
6. Design data ingestion, transformation, and indexing pipelines for structured and unstructured data.
7. Ensure high availability, scalability, and security of database systems across environments.
8. Develop scalable microservices and APIs for AI-powered applications.
9. Integrate AI solutions with enterprise systems (CRM, ERP, DMS) using secure and performant architectures.
10. Define SLAs, performance benchmarks, and monitoring strategies for AI services.
11. Implement data governance policies for AI and database systems.
12. Ensure compliance with data privacy regulations (GDPR, HIPAA, etc.).
13. Collaborate with InfoSec teams to secure AI pipelines and data assets.
Experience: >10 YEARS .
Reinvent your world. We are building a modern Wipro. We are an end-to-end digital transformation partner with the boldest ambitions. To realize them, we need people inspired by reinvention. Of yourself, your career, and your skills. We want to see the constant evolution of our business and our industry. It has always been in our DNA - as the world around us changes, so do we. Join a business powered by purpose and a place that empowers you to design your own reinvention. Come to Wipro. Realize your ambitions. Applications from people with disabilities are explicitly welcome.