Job Overview

Birlasoft is hiring a Generative AI Developer for an experienced software engineering role with opportunities in Noida, Hyderabad, Bengaluru, Pune, Chennai, and Mumbai. The position focuses on building production-oriented Generative AI applications rather than limiting development to early proof-of-concept work.

The role combines Python engineering, large language model frameworks, multimodal AI, data engineering, model fine-tuning, retrieval-augmented generation, LLMOps, cloud deployment, frontend integration, document intelligence, API integration, and responsible AI. The developer will help create scalable AI solutions that can work with structured and unstructured data while supporting practical enterprise use cases.

Key Responsibilities

• Build Generative AI applications from the ground up using modern LLM application frameworks.
• Develop maintainable and efficient Python components for AI applications, automation, data processing, and integrations.
• Work with AutoGen, CrewAI, LangGraph, LlamaIndex, and LangChain to create AI workflows and agent-oriented applications.
• Design architectures capable of handling large volumes of structured and unstructured data.
• Develop applications using text, vision, and speech model capabilities.
• Fine-tune Small Language Models for specific domains, datasets, and business use cases.
• Integrate GenAI backends with interfaces built using React, Streamlit, AG Grid, and JavaScript.
• Design data modernization and transformation pipelines that prepare information for AI applications.
• Apply PEFT, QLoRA, LoRA, and related techniques when adapting language models for targeted requirements.
• Implement LLMOps practices for model deployment, monitoring, lifecycle management, and operational reliability.
• Apply responsible AI principles throughout the development lifecycle.
• Support prompt-injection testing and related AI security considerations using relevant tools.
• Work with approaches for evaluating model output quality and reducing hallucinations or low-quality responses.
• Build RAG and Modular RAG solutions for applications that need grounded responses from enterprise data.
• Develop OCR and document intelligence capabilities using cloud-based services.
• Integrate AI applications with other systems through REST, SOAP, and related API protocols.
• Create automated data curation and preprocessing workflows.
• Prepare clear technical documentation covering application architecture, implementation, workflows, and operational practices.

Required Skills

Strong Python programming experience is central to this position. Candidates should be able to develop production-quality GenAI applications and automation tools with attention to maintainability, scalability, testing, and operational requirements.

Hands-on experience with LLM application frameworks is expected. Relevant frameworks include AutoGen, CrewAI, LangGraph, LlamaIndex, and LangChain. Candidates should understand how these tools can support AI workflows, retrieval systems, agent-based applications, and enterprise integrations.

The role requires experience with productionizing GenAI solutions beyond PoCs. Knowledge of scaling, quality controls, security considerations, monitoring, and engineering practices is important for delivering dependable applications.

Candidates should understand large-scale data handling, including structured and unstructured data architectures, data transformation, curation, and preprocessing. Experience with multimodal solutions involving text, vision, or speech is relevant.

Required Technologies

• Python
• Generative AI
• Large Language Models (LLMs)
• AutoGen
• CrewAI
• LangGraph
• LlamaIndex
• LangChain
• RAG
• Modular RAG
• Small Language Models (SLMs)
• PEFT
• QLoRA
• LoRA
• LLMOps
• Responsible AI
• React
• Streamlit
• AG Grid
• JavaScript
• Azure
• Google Cloud Platform (GCP)
• AWS
• REST
• SOAP
• API Integration
• OCR
• Document Intelligence
• Data Modernization
• Data Curation
• Data Preprocessing
• Multimodal AI
• Text Models
• Vision Models
• Speech Models
• Pyrit
• Pylint
• HAX Toolkit
• BLEU

Preferred Skills

Experience with at least two of the listed cloud platforms, including Azure, GCP, or AWS, is useful for this role. Candidates with practical exposure to any one of PEFT, QLoRA, or LoRA can also align with the stated requirements.

Knowledge of prompt-injection testing, AI security tooling, model-output evaluation, and techniques for reducing hallucinations can strengthen a candidate's profile. Experience with Pyrit, HAX Toolkit, BLEU, or similar tools should be described accurately based on actual usage.

Experience with OCR, document intelligence, RAG, Modular RAG, automated data curation, and cloud-based AI services is valuable for enterprise GenAI development.

Soft Skills

The role requires strong collaboration and communication because GenAI applications typically involve multiple technical and business disciplines. Candidates should be able to explain architecture decisions, AI capabilities, limitations, integration approaches, and implementation risks clearly.

A practical problem-solving mindset is important when working with evolving AI frameworks and model behavior. The ability to investigate issues, test alternatives, document findings, and improve solutions is valuable.

Technical documentation is also part of the role. Candidates should be comfortable creating clear documentation that helps engineering teams understand application workflows, data processing, integrations, and operational requirements.

Benefits of Working in this Role

This role provides broad exposure to the modern Generative AI engineering lifecycle. Developers can work across AI application development, agent workflows, RAG, multimodal capabilities, model adaptation, data modernization, cloud deployment, LLMOps, and responsible AI.

The position can help experienced software engineers strengthen enterprise AI skills through exposure to multiple cloud platforms and modern AI engineering frameworks. Productionization, security, evaluation, and data pipeline experience can support long-term growth in AI engineering.

Work Mode

The provided job description does not explicitly state whether the role is onsite, hybrid, or remote. It specifies multiple job locations but does not identify a work mode.

Location

The position is listed for Noida, Hyderabad, Bengaluru, Pune, Chennai, and Mumbai, India.

Who Should Apply

This opportunity is suitable for professionals with 4 or more years of experience who have practical experience developing Generative AI applications. Candidates should have strong Python skills and hands-on exposure to LLM frameworks, cloud platforms, data architecture, or AI application engineering.

Applicants with experience in RAG, AI agents, multimodal AI, LLM fine-tuning, LLMOps, OCR, document intelligence, API integration, and data curation are particularly relevant. The role is aimed at experienced professionals rather than freshers.

Career Growth

Experience in this position can support progression into roles such as Senior Generative AI Engineer, AI Application Architect, LLM Engineer, AI Solutions Architect, LLMOps Engineer, AI Platform Engineer, or Enterprise AI Technical Lead.

Application Advice

Highlight production GenAI applications you have built instead of listing only courses or prototypes. Clearly mention your Python experience and the LLM frameworks you have actually used.

If you have worked with AutoGen, CrewAI, LangGraph, LlamaIndex, or LangChain, explain the type of workflows or applications you developed. Include practical experience with RAG, Modular RAG, AI agents, multimodal models, fine-tuning, LLMOps, or cloud deployment where applicable.

Candidates should identify the cloud platforms they have used among Azure, GCP, and AWS. Mention experience with React, Streamlit, AG Grid, JavaScript, REST, SOAP, OCR, document intelligence, and data pipelines when relevant.

For AI security and quality work, describe actual experience with prompt-injection testing, Pyrit, HAX Toolkit, BLEU, or similar evaluation and security approaches. Keep all claims accurate and demonstrate measurable engineering outcomes where possible.