Python ML_GenAI Engineers

Infosys; Chennai District; On-site; INR 1,200,000 - 2,500,000; Full time

Job summary

Infosys in Chennai is seeking engineers to design and deploy GenAI solutions. You will build scalable data pipelines for both structured and unstructured data, implement RAG systems, and integrate LLMs with enterprise apps via APIs and workflows.

The role emphasizes cloud-native AI services across AWS, Azure, GCP, and Databricks, with LangChain/LangGraph-powered agent solutions and strong focus on data quality and security.

Qualifications

• 1+ years of GenAI/LLM development experience.
• Experience with production-grade GenAI solutions.
• Familiarity with knowledge graphs and semantic search.

Responsibilities

• Design and develop GenAI applications using Python and enterprise LLM platforms.
• Build scalable data pipelines for structured and unstructured data processing.
• Implement Retrieval-Augmented Generation (RAG) systems and vector-based search.
• Integrate LLMs with enterprise applications via APIs and workflows.
• Develop cloud-native AI services on AWS, Azure, GCP, Databricks (DBRX), or Snowflake.
• Create agent-based solutions using LangChain and LangGraph.
• Ensure data quality, governance, and security compliance across AI workflows.
• Optimize performance, scalability, and reliability of AI solutions.

Skills

Python

SQL

ETL/ELT

Data Modeling

Data Quality

Cloud-native Development

API Integration

Data Engineering

RAG

Prompt Engineering

LangChain

LangGraph

OpenAI API

Tools

Hugging Face

LangChain

LangGraph

OpenAI

Anthropic

Gemini

Job description

Job Description

Python, SQL, ETL/ELT, Data Modeling, Data Quality, Cloud-native Development, API Integration, Data Engineering, ETL, Document Processing, Workflow design, knowledge of LLM development, RAG, Prompt Engineering, AI Coding Assistants Advanced Skills: RAG Data Pipelines, LLM Data Integration, AI Service Integration, Scalable AI Deployments, Agent Orchestration, Tool Calling, LangGraph, LangChain

• Design and develop GenAI applications using Python and enterprise LLM platforms. 2. Build scalable data pipelines for structured and unstructured data processing. 3. Implement Retrieval-Augmented Generation (RAG) systems and vector-based search solutions. 4. Integrate LLMs with enterprise applications through APIs and workflows. 5. Develop cloud-native AI services on AWS, Azure, GCP, Databricks (DBRX), or Snowflake. 6. Create agent-based solutions using LangChain and LangGraph. 7. Ensure data quality, governance, and security compliance across AI workflows. 8. Optimize performance, scalability, and reliability of AI solutions.
• 1+ years of experience with Hugging Face, LangChain, OpenAI, Anthropic, Gemini, or open-source LLMs. 2. Familiarity with knowledge graphs and semantic search. 3. Experience building production-grade GenAI solutions