Generative AI Engineer

Persistent Systems; Bengaluru; On-site; INR 4,000,000 - 7,000,000; Full time

Job summary

Persistent Systems is seeking an experienced Gen AI engineer to design and deliver scalable Gen AI solutions in Python. You will build AI workflows and agent-based applications using LangChain and LangGraph, and integrate LLM-powered solutions with APIs, databases, and vector stores.

Collaborate with data scientists, architects and business stakeholders to deploy production-grade Gen AI apps, master prompt engineering, RAG, tool calling and AI workflow orchestration while optimizing performance,

Qualifications

• 9–12 years of software development experience with strong Python expertise.
• Strong hands-on experience in Generative AI and LLM application development.
• Mandatory experience with LangChain and LangGraph.
• Strong understanding of LLMs, RAG, Prompt Engineering, AI Agents, and Vector Databases.
• Experience building and deploying production-grade Gen AI applications.
• Strong knowledge of REST APIs, microservices, and cloud-based application development.

Responsibilities

• Design and develop Generative AI applications and solutions using Python.
• Build AI workflows and agent-based applications using LangChain and LangGraph.
• Develop and integrate LLM-powered apps, AI agents, and intelligent automation.
• Design scalable, production-ready Gen AI solutions for enterprise use cases.
• Integrate LLMs with APIs, databases, vector stores, and external services.
• Implement prompt engineering, RAG, tool calling, and AI workflow orchestration.

Skills

Python

Generative AI

LLM development

Problem solving

Communication

Technical design

Cloud-based development

REST APIs

Microservices

AI agents

Tools

LangChain

LangGraph

Job description

• Design and develop Generative AI applications and solutions using Python.
• Build AI workflows and agent-based applications using LangChain and LangGraph.
• Develop and integrate LLM-powered applications, AI agents, and intelligent automation solutions.
• Design scalable and production-ready Gen AI solutions for enterprise use cases.
• Integrate LLMs with APIs, databases, vector stores, and external services.
• Implement prompt engineering, RAG, tool calling, and AI workflow orchestration.
• Optimize AI applications for performance, scalability, reliability, and cost.
• Collaborate with data scientists, engineers, architects, and business stakeholders.

Eligibility / Required Skills

• 9-12 years of overall software development experience with strong Python expertise.
• Strong hands-on experience in Generative AI and LLM application development.
• Mandatory experience with LangChain and LangGraph.
• Strong understanding of LLMs, RAG, Prompt Engineering, AI Agents, and Vector Databases.
• Experience building and deploying production-grade Gen AI applications.
• Strong knowledge of REST APIs, microservices, and cloud-based application development.
• Excellent problem-solving, communication, and technical design skills.