Generative AI Engineer

Persistent

8–12 yrs Pune Full Time Hybrid (office + remote)
Persistent logo
Posted : today
Actively hiring

Job description

Join Persistent as a Generative AI Engineer focused on Agentic AI and Survey Automation. You will play a key role in designing, developing, and optimizing advanced AI agents to streamline survey programming and data processing workflows.

This position offers the opportunity to leverage cutting-edge technologies like Large Language Models (LLMs), Agentic AI frameworks, Retrieval-Augmented Generation (RAG), and Azure OpenAI to build intelligent solutions. Your work will directly contribute to enhancing operational efficiency and automating complex business processes with high accuracy.

Persistent is a leading AI-led, platform-driven Digital Engineering and Enterprise Modernization partner, collaborating with global industry leaders. We foster a values-driven, people-centric, and inclusive work environment, committed to diversity and talent development.

Responsibilities

Design, develop, and deploy sophisticated AI agents utilizing Python, LangGraph, Microsoft Agent Framework, and Azure OpenAI.

Build and refine Survey Programming Agents covering tasks such as Questionnaire Parsing, Routing Logic, JSON Generation, Dimensions Setup, STG Generation, Translation Workflows, DMS Script Creation, Link Testing, Survey Quality Control, and Change Impact Analysis.

Develop and enhance Data Processing Agents for Quantum Programming, Tabulation, Weighting, Cross-Tab Detection, Open-End Coding Merge, SPSS/PKD Setup, and Quality Control.

Implement Retrieval-Augmented Generation (RAG) pipelines and intelligent agent workflows for enterprise-scale automation.

Design robust reasoning workflows, confidence-scoring mechanisms, and evidence-generation frameworks to elevate AI decision-making.

Construct exception-handling frameworks and Human-in-the-Loop (HITL) review processes for critical workflows.

Develop agent observability and monitoring capabilities to track performance, quality, and accuracy.

Integrate Large Language Models with enterprise platforms, APIs, and business processes.

Create and optimize JSON schema designs for structured AI outputs and workflow orchestration.

Execute prompt engineering, prompt optimization, and model evaluations to enhance AI response quality.

Perform automated evaluation loops against golden datasets and benchmark results against predefined quality targets.

Engage in model fine-tuning and optimization activities to improve domain-specific performance.

Collaborate with business stakeholders, data teams, and engineering teams to identify automation opportunities and deliver scalable AI solutions.

Maintain comprehensive technical documentation, evaluation reports, and adhere to AI governance standards.

Qualifications

Possess 8 to 12 years of experience in software engineering, AI engineering, or machine learning.

Demonstrate strong programming expertise in Python.

Have hands-on experience with Large Language Models (LLMs) and enterprise AI application development.

Show significant experience working with Azure OpenAI Services and LLM integrations.

Proven experience building Agentic AI solutions using frameworks like LangGraph, Microsoft Agent Framework, or LangChain.

Exhibit a strong understanding of Retrieval-Augmented Generation (RAG) architectures and retrieval optimization techniques.

Possess expertise in Prompt Engineering, prompt evaluation, and prompt optimization methodologies.

Have experience designing and implementing JSON schemas, structured outputs, and workflow-driven AI systems.

Familiarity with AI evaluation frameworks, benchmarking methodologies, and quality scoring techniques.

Experience building AI agents that automate business workflows and decision-making processes is essential.

Strong understanding of model fine-tuning, evaluation, and performance optimization.

Experience implementing observability, monitoring, and operational frameworks for AI systems.

Familiarity with REST APIs, cloud-native architectures, and microservices-based systems.

Excellent analytical, troubleshooting, and problem-solving skills are required.

Strong communication and stakeholder management capabilities are crucial.

Experience working in Agile, Scrum, or modern product engineering environments is beneficial.

Essential Skills

PythonLarge Language Models (LLMs)Agentic AIRetrieval-Augmented Generation (RAG)Azure OpenAILangGraphMicrosoft Agent FrameworkLangChainPrompt EngineeringJSON SchemaREST APIsCloud-Native ArchitecturesMicroservices

Highlights

  • Actively hiring

More Details

RoleGenerative AI Engineer
DepartmentSoftware Development
Employment TypeFull Time, Hybrid (office + remote)

About the Company

Persistent Systems logo

Persistent Systems

IT Consulting

Generative AI Engineer at Persistent | SkillMX | SkillMX