GenAI Engineer: LLMs, RAG & Vector AI

Infosys; Charlotte (TX); On-site; USD 120,000 - 180,000; Full time

Job summary

Infosys is seeking a Technology Consultant 2 to drive AI-driven digital transformation for financial services. You will engage in requirements elicitation, design discussions, coding, testing, and documentation across banking, wealth management, and insurance projects.

Key focus areas include Generative AI, LLMs, RAG-based apps, document processing, embedding models, semantic search, and LangChain/Graph frameworks. Strong Python and cloud platform experience preferred.

Qualifications

• Bachelor's degree or foreign equivalent; progressive experience accepted in lieu of education.
• Willingness to relocate and travel to work/project locations in the US.
• Candidates authorized to work in the US without visa sponsorship.

Responsibilities

• Contribute to requirements elicitation, documenting business needs with guidance.
• Facilitate design discussions and document decisions for the software team.
• Participate in coding, integrating new features while maintaining stability.
• Conduct code reviews, update codebase, and maintain repositories.
• Implement test strategies, analyze results, and coordinate fixes.
• Develop user training materials and support frameworks for new apps.
• Resolve production issues and propose preventive reliability measures.
• Maintain detailed records of code, testing techniques, and support activities.

Skills

Generative AI

LLMs

RAG-based apps

Document Processing

Embedding Models

Semantic Search

Vector Indexing

LangChain

LangGraph

Agentic AI

Vector Databases

Python

PySpark

AWS

Azure

GCP

Cloudera Hadoop

Education

Bachelor's degree

Tools

PySpark

Cloudera Hadoop

AWS

Azure

GCP

Job description

Infosys is seeking a Technology Consultant 2 to drive AI-driven digital transformation for financial services. You will engage in requirements elicitation, design discussions, coding, testing, and documentation across banking, wealth management, and insurance projects.

Key focus areas include Generative AI, LLMs, RAG-based apps, document processing, embedding models, semantic search, and LangChain/Graph frameworks. Strong Python and cloud platform experience preferred.