GEN AI Developer

Birlasoft; Pune District; On-site; INR 1,500,000 - 2,100,000; Full time

Job summary

Birlasoft in Pune district, India seeks a GEN AI Developer with 4–6 years of experience to design and implement GenAI applications. You will work on multi-modal models, data pipelines, and LLM fine-tuning with modern frameworks, ensuring scalable production readiness.

Role involves building interfaces, integrating front-end technologies, and ensuring responsible AI practices across projects, with immediate availability desired.

Qualifications

• Deep expertise in Python for GenAI applications and automation.
• Experience building GenAI apps from scratch using modern frameworks.
• Designing architectures for large-scale structured and unstructured data.

Responsibilities

• Build GenAI applications from scratch using frameworks like Autogen, Crew.ai, LangGraph, LlamaIndex, and LangChain.
• Develop high-quality, efficient Python code for GenAI solutions.
• Design architectures for handling large-scale data.
• Familiarity with text chat, vision, and speech models.
• Fine-tune small language models for domain data.
• Create user interfaces with React/Streamlit for GenAI backends.
• Build data modernization pipelines for GenAI apps.
• Apply PEFT/QLoRA/LoRA for tuning LLMs.
• Set up LLMOps CI/CD and monitoring pipelines.
• Embed Responsible AI practices in development.

Skills

Python Programming

GenAI development

LLM Frameworks

Front-End integration

Large-scale data architecture

Multimodal LLM applications

Fine-tuning LLMs

LLMOps pipelines

Responsible AI practices

API integration

Front-end technologies

OCR and document intelligence

Tools

Autogen

Crew.ai

LangGraph

LlamaIndex

LangChain

Pylint

Pyrit

HAX toolkit

Bleu

Streamlit

React

AG Grid

Azure

GCP

AWS

Job description

• Application Development: Build GenAI applications from scratch using frameworks like Autogen (applied or acquired), Crew.ai, LangGraph, LlamaIndex, and LangChain.
• Python Programming: Develop high-quality, efficient, and maintainable Python code for GenAI solutions.
• Large-Scale Data Handling & Architecture: Design and implement architectures for handling large-scale structured and unstructured data.
• Multi-Modal LLM Applications: Familiarity with text chat completion, vision, and speech models.
• Fine-tune SLM(Small Language Model) for domain specific data and use cases.
• Front-End Integration: Implement user interfaces using front-end technologies like React, Streamlit, and AG Grid, ensuring seamless integration with GenAI backends.
• Data Modernization and Transformation: Design and implement data modernization and transformation pipelines to support GenAI applications.
• Fine-Tuning LLMs: Apply fine-tuning techniques such as PEFT, QLoRA, and LoRA to optimize LLMs for specific use cases.
• LLMOps Implementation: Set up and manage LLMOps pipelines for continuous integration, deployment, and monitoring.
• Responsible AI Practices: Ensure ethical AI practices are embedded in the development process.

Long Description

Role - GEN AI Developer

Exp - 4-6 years

NP - Imemdiate Only

Key Responsibilities

• Application Development: Build GenAI applications from scratch using frameworks like Autogen (applied or acquired), Crew.ai, LangGraph, LlamaIndex, and LangChain.
• Python Programming: Develop high-quality, efficient, and maintainable Python code for GenAI solutions.
• Large-Scale Data Handling & Architecture: Design and implement architectures for handling large-scale structured and unstructured data.
• Multi-Modal LLM Applications: Familiarity with text chat completion, vision, and speech models.
• Fine-tune SLM(Small Language Model) for domain specific data and use cases.
• Front-End Integration: Implement user interfaces using front-end technologies like React, Streamlit, and AG Grid, ensuring seamless integration with GenAI backends.
• Data Modernization and Transformation: Design and implement data modernization and transformation pipelines to support GenAI applications.
• Fine-Tuning LLMs: Apply fine-tuning techniques such as PEFT, QLoRA, and LoRA to optimize LLMs for specific use cases.
• LLMOps Implementation: Set up and manage LLMOps pipelines for continuous integration, deployment, and monitoring.
• Responsible AI Practices: Ensure ethical AI practices are embedded in the development process.

Required Skills

• Python Programming: Deep expertise in Python for building GenAI applications and automation tools.
• Productionization of GenAI application beyond PoCs – Using scale frameworks and tools such as Pylint,Pyrit etc.
• LLM Frameworks: Proficiency in frameworks like Autogen, Crew.ai, LangGraph, LlamaIndex, and LangChain.
• Large-Scale Data Handling & Architecture: Design and implement architectures for handling large-scale structured and unstructured data.
• Multi-Modal LLM Applications: Familiarity with text chat completion, vision, and speech models.
• Fine-tune SLM(Small Language Model) for domain specific data and use cases.
• Prompt injection fallback and RCE tools such as Pyrit and HAX toolkit etc.
• Anti-hallucination and anti-gibberish tools such as Bleu etc.
• Front-End Technologies: Strong knowledge of React, Streamlit, AG Grid, and JavaScript for front-end development.
• Cloud Platforms: Extensive experience with Azure, GCP, and AWS for deploying and managing GenAI applications. (any two cloud exp.)
• Fine-Tuning Techniques: Mastery of PEFT, QLoRA, LoRA, and other fine-tuning methods. (any one is fine)
• LLMOps: Strong knowledge of LLMOps practices for model deployment, monitoring, and management.
• Responsible AI: Expertise in implementing ethical AI practices and ensuring compliance with regulations.
• RAG and Modular RAG: Advanced skills in Retrieval-Augmented Generation and Modular RAG architectures.
• Data Modernization: Expertise in modernizing and transforming data for GenAI applications.
• OCR and Document Intelligence: Proficiency in OCR and document intelligence using cloud-based tools.
• API Integration: Experience with REST, SOAP, and other protocols for API integration.
• Data Curation: Expertise in building automated data curation and preprocessing pipelines.
• Technical Documentation: Ability to create clear and comprehensive technical documentation.
• Collaboration and Communication: Strong collaboration and communication skills to work effectively with cross‑functional teams.
• innovation.

Target Companies – Quantiphi,Datastax,Coforge,HCL,Accenture,Fractal.