Description

You will architect and implement modern AI infrastructure focusing on Vector Databases and Retrieval-Augmented Generation (RAG).

Responsibilities

• Architect end-to-end AI/ML systems and integrate RAG frameworks with Vector Databases.
• Define and deploy AI-powered search and knowledge systems.
• Collaborate with stakeholders on data embedding, indexing, and semantic retrieval.
• Guide the roadmap for Generative AI adoption and ensure system scalability.
• Work independently to deliver production-ready AI solutions.

Required Skills

• 10+ years in software architecture/system design, with 5+ years in AI/ML.
• Hands-on experience with Vector Databases (Pinecone, Milvus, Weaviate, FAISS).
• Proven expertise in RAG frameworks and LLM integration.
• Strong skills in Python, LangChain, or similar tools.
• Deep knowledge of semantic search, data embedding, and prompt engineering.
• Experience with AWS, Azure, or GCP cloud platforms.
• Stakeholder Management experience.

Preferred Skills

• Master’s/Ph.D. in Computer Science, AI/ML, or Data Engineering.
• Experience building enterprise-scale AI search systems.

Key Skills

Education

Master’s/Ph.D. in Computer Science