Q2C Senior Specialist

Kantar; Gurugram District; Hybrid; INR 1,800,000 - 3,200,000; Full time

Job summary

Fujitsu seeks a GenAI - Application Developer to build GenAI and Agentic AI solutions, working with LLMs, prompts, APIs, vector databases and enterprise data sources. You will support development, testing, deployment and production support.

You will collaborate with architects, senior developers, business teams and delivery teams in a multi-region setup. Remote/hybrid options may apply depending on project needs and client shifts.

Qualifications

• GenAI application development.
• Agentic AI concepts and implementation.
• Prompt engineering.
• RAG implementation.
• LLM API integration.
• Python.
• REST API development and integration.
• SQL and basic data handling.
• Vector database and embeddings basics.
• Git-based development.

Responsibilities

• Understand business use cases for GenAI and Agentic AI solutions.
• Clarify user needs, expected output, data sources, and workflow steps.
• Identify solution type (chatbot, RAG, agent, automation, or decision-support).
• Work with architect and senior developers to finalize technical approach.
• Support estimation for tasks.
• Develop GenAI features using Python or approved tech stack.
• Build LLM-based chat, search, summarization, and QA features.
• Create and improve prompts; develop agent workflows calling tools/apis.
• Integrate LLM APIs with backend; connect to enterprise data sources.
• Configure vector databases and document retrieval pipelines.
• Build secure, maintainable code with CI/CD alignment.
• Test prompts, validate RAG outputs, perform unit/integration tests.
• Ensure error handling and fallback paths in agent workflows.

Skills

GenAI application development

Agentic AI concepts

Prompt engineering

RAG implementation

LLM API integration

Python

REST API development

SQL

Vector database

Git-based development

Tools

LangChain

LangGraph

LlamaIndex

OpenAI

Azure OpenAI

Claude

Gemini

AWS Bedrock

FastAPI

Flask

Job description

Job Title: GenAI - Application Developer - 11313

Location: Pune

Shift: 2:00 PM-11:00 PM

Experience: 3-5 Years

Job Description AI Developer - GenAI / Agentic AI

Experience: 3+ years

Flexible based on hands-on fit. Candidates with strong AI project experience can also be considered.

Location / Shift:

• India / Remote / Hybrid / Work from Office as per project need
• Client shift may apply
• Multi-region team collaboration may be required

Role Summary

You will develop GenAI and Agentic AI solutions. You will build AI assistants, RAG-based solutions, and agent workflows. You will work with LLMs, prompts, APIs, tools, vector databases, and enterprise data sources. You will support development, testing, deployment, and production support. You will work with architects, senior developers, business teams, and delivery teams.

Primary Skills

Must Have

• GenAI application development
• Agentic AI concepts and implementation
• Prompt engineering
• RAG implementation
• LLM API integration
• Python
• REST API development and integration
• SQL and basic data handling
• Vector database and embeddings basics
• Git-based development

Good to Have

• LangChain / LangGraph / LlamaIndex
• OpenAI / Azure OpenAI / Claude / Gemini / AWS Bedrock
• Agent tools, function calling, and workflow orchestration
• Model Context Protocol
• FastAPI / Flask / Node.js
• Docker and basic CI/CD
• Cloud basics: Azure / AWS / GCP
• LLM evaluation and observability basics
• Responsible AI and AI governance awareness

Key Responsibilities

1) Requirement Understanding

• Understand business use cases for GenAI and Agentic AI solutions.
• Clarify user needs, expected output, data sources, and workflow steps.
• Understand whether the solution needs chatbot, RAG, agent, automation, or decision-support capability.
• Identify assumptions, dependencies, risks, and open points.
• Work with architect and senior developers to finalize technical approach.
• Support estimation for assigned tasks.

2) Solution Design

• Support low-level design for assigned AI modules.
• Design prompt flow, API flow, and response flow for assigned features.
• Support RAG design using approved enterprise documents or databases.
• Help define agent workflow steps, tools, fallback handling, and human review points.
• Keep design simple, secure, and easy to maintain.
• Follow architecture guidance and project standards.

3) Development / Implementation

• Develop GenAI features using Python or other approved technology stack.
• Build LLM-based chat, search, summarization, classification, and QA features.
• Develop RAG pipelines using embeddings, vector search, and retrieval logic.
• Create and improve prompts for better response quality.
• Build agent workflows that can call tools, APIs, or backend services.
• Implement structured outputs like JSON where required.
• Write clean, readable, and maintainable code.
• Follow coding standards, branch process, and code review comments.

4) Integration / Configuration

• Integrate LLM APIs with application backend.
• Connect AI solutions with enterprise systems, APIs, files, databases, and knowledge sources.
• Configure vector databases and document retrieval pipelines.
• Configure environment variables, model settings, API keys, and service connections securely.
• Support tool-use / function-calling implementation for agents.
• Support integration with cloud services where needed.
• Work with DevOps and platform teams for environment setup.

5) Testing Validation

• Test prompts with different user scenarios.
• Validate RAG responses against source documents.
• Perform unit testing and integration testing for assigned components.
• Test agent workflows, tool calls, API calls, and fallback paths.
• Validate AI output for accuracy, relevance, safety, and consistency.
• Fix defects found during testing and UAT.
• Prepare test evidence and validation notes.

6) Performance Optimization

• Improve prompt quality and reduce unnecessary model calls.
• Optimize retrieval logic, chunking, metadata filters, and context usage.
• Support response time and token usage optimization.
• Tune API calls, retry logic, timeout, and caching where required.
• Identify weak responses and suggest improvement actions.
• Support cost-aware design and efficient execution.

7) Security, Compliance Governance

• Follow secure coding and data handling practices.
• Use only approved data sources and approved APIs.
• Avoid exposing API keys, tokens, passwords, or confidential data.
• Support access control and audit logging as per design.
• Follow responsible AI guidelines for safe and reliable output.
• Add guardrails and validation checks where required.
• Escalate data privacy or unsafe-output concerns early.

8) Deployment Release Management

• Support deployment across Dev / Test / UAT / Prod environments.
• Prepare code changes for review and release.
• Follow Git and CI/CD process as per project setup.
• Support release notes and deployment checklist preparation.
• Perform post-deployment validation.
• Support rollback or quick fix activities when required.

9) Production Support RCA

• Support production issues related to AI responses, APIs, retrieval, agents, and latency.
• Check logs and identify basic failure reasons.
• Debug issues related to wrong answers, missing context, tool failure, or API errors.
• Provide RCA inputs for recurring issues.
• Implement fixes with proper testing.
• Support hypercare after production release.

10) Documentation Knowledge Transfer

• Prepare technical notes for assigned AI components.
• Document prompt behavior, API usage, RAG flow, tool flow, and configuration steps.
• Maintain test cases and validation results.
• Update support notes and runbooks where required.
• Share implementation details with team members.
• Support knowledge transfer to QA, support, and delivery teams.

11) Agile Delivery Collaboration

• Work in Agile/Scrum delivery model.
• Participate in daily stand-ups, sprint planning, reviews, and retrospectives.
• Provide clear daily updates on progress, blockers, and next steps.
• Work closely with AI architects, senior developers, QA, business analysts, and DevOps teams.
• Take ownership of assigned stories and deliver on time.
• Raise risks and blockers early.

Tools / Technologies

• Cloud / Platform: Azure / AWS / GCP
• AI Tools: OpenAI, Azure OpenAI, Claude, Gemini, AWS Bedrock, local/open-source LLMs
• Agentic AI Tools: LangChain, LangGraph, LlamaIndex, Agents SDK, MCP
• Data Tools: Vector databases, embeddings, document parsers, RAG pipeline
• Database / Warehouse: PostgreSQL, SQL Server, MongoDB, Vector DB
• Programming Languages: Python, JavaScript / TypeScript, SQL
• API / Backend: FastAPI, Flask, Node.js, REST APIs
• DevOps Tools: Git, GitHub, Azure DevOps, Docker, CI/CD basics
• Monitoring Tools: Application logs, API logs, cloud monitoring, LLM evaluation logs
• Documentation Tools: Jira, Confluence, SharePoint, Azure Boards

Qualification

• BE / BTech / MCA / MSc / BSc / BCA or equivalent practical experience
• AI / GenAI / Cloud / Python certification is good to have
• Hands-on project experience in chatbot, RAG, LLM, AI agent, or automation use case is preferred

Soft Skills

• Clear communication
• Strong learning mindset
• Ownership of assigned work
• Good problem-solving ability
• Team collaboration
• Curiosity to learn new AI tools
• Good documentation habit

Delivery-focused mindset

Relocation Supported: No

Visa Sponsorship Approved: No

At Fujitsu, we are committed to an inclusive recruitment process that values the diverse backgrounds and experiences of all applicants. We believe that hiring people from a wide variety of backgrounds makes us stronger, not because it''s the right thing to do, but because it allows us to draw on a wider range of perspectives and life experiences.