Staff AI Engineer - Vector Store & RAG Platform

Teradata; India (PA); Hybrid; USD 160,000 - 210,000; Full time

Job summary

Teradata is seeking a Staff AI Engineer to shape the vector store and retrieval infrastructure at enterprise scale. You will own the architecture and drive core platform capabilities for RAG, semantic search, and agentic AI, collaborating with AI architects, ML engineers, and cross-functional teams.

This role emphasizes a strong foundation in distributed systems, LLMs, and scalable data processing, delivering production-grade features and evaluating performance across diverse workloads.

Qualifications

• BS/MS/PhD in Computer Science, AI/ML, or a related field.
• 8+ years of professional software engineering experience, ownership of complex systems.
• Deep expertise in vector search, information retrieval, or semantic search systems.
• Proven experience designing and deploying production-grade RAG platforms.
• Strong knowledge of embeddings, context optimization, and retrieval approaches.
• Proficiency in Python (and/or Java) and production-grade systems.

Responsibilities

• Own architecture and technical direction of Teradata’s vector store.
• Define design patterns for RAG, semantic search, and agentic AI.
• Lead design reviews and cross-team architectural decisions.
• Identify scalability, performance, and reliability risks.
• Design agentic AI patterns: tool calls, memory, orchestration.
• Implement vector store capabilities: indexing, storage, retrieval, APIs.
• Build RAG evaluation frameworks: relevance, faithfulness, accuracy, cost.
• Collaborate with product and platform teams to translate use cases into features.
• Benchmark against cloud/open-source solutions.
• Contribute to long-term AI platform strategy.

Skills

Vector search

Information retrieval

Semantic search

Python

Distributed systems

Education

BS/MS/PhD in Computer Science, AI/ML, or a related field

Tools

LangChain

LangGraph

AWS

Azure

GCP

Job description

Teradata is seeking a Staff AI Engineer to shape the vector store and retrieval infrastructure at enterprise scale. You will own the architecture and drive core platform capabilities for RAG, semantic search, and agentic AI, collaborating with AI architects, ML engineers, and cross-functional teams.

This role emphasizes a strong foundation in distributed systems, LLMs, and scalable data processing, delivering production-grade features and evaluating performance across diverse workloads.