Generative AI Developer

Location: Chennai / Bangalore / Gurgaon (NCR)

Type: Full-time

Role Overview

We are looking for a passionate and skilled Generative AI Developer to join our Generative AI Center of Excellence (CoE). In this role, you will be at the forefront of developing innovative AI solutions, leveraging Large Language Models (LLMs) and generative technologies to solve complex business problems for our clients and internal teams.

Key Responsibilities

• Solution Development: Design, build, and deploy Generative AI applications using foundation models (e.g., OpenAI GPT, Llama, Claude) and frameworks like Langchain, Google ADK and Microsoft Agentic Framework.


• Prompt Engineering: Develop and optimize advanced prompt strategies and techniques (Chain-of-Thought, Few-Shot) to maximize model performance.


• RAG Implementation: Design and implement Retrieval-Augmented Generation (RAG) pipelines using vector databases (Pinecone, Weaviate, Milvus) and orchestration frameworks (LangChain, LlamaIndex).


• Model Fine-Tuning: Fine-tune and customize LLMs for specific domains and use cases using techniques like PEFT/LoRA.


• Version Control: Manage code repositories using Git, follow branching strategies, and participate in code reviews.


• Integration: Integrate AI models into existing applications and workflows, ensuring scalability and reliability.


• Evaluation: Implement frameworks for evaluating and monitoring model performance, bias, and safety.


• Research: Stay updated with the latest advancements in Generative AI and emerging technologies.


• Cost Optimization: Monitor and optimize API usage, token consumption, and cloud resource costs for AI solutions.

Qualifications

• Experience: 3+ years of experience in AI/ML, with a specific focus on Generative AI and LLMs in recent projects.


• Programming: Strong proficiency in Python and standard ML libraries (PyTorch, TensorFlow, Transformers).


• GenAI Stack: Hands-on experience with LangChain /Google ADK/MS Agentic Frameworks, and vector databases.


• API Integration: Experience working with APIs from OpenAI, Anthropic, Azure OpenAI, or Hugging Face.


• Cloud: Experience deploying AI models and working with AI offerings on cloud platforms (Azure, AWS, GCP).


• SQL: Proficiency in SQL for data querying and managing structured data.


• Version Control: Proficiency with Git and repository management (GitHub, GitLab, Azure Repos).


• Containerization: Familiarity with Docker for packaging and deploying AI applications.

Preferred Skills

• Experience with Agentic workflows (AutoGPT, LangGraph).


• Knowledge of MLOps practices for LLMs (LLMOps).


• Background in Natural Language Processing (NLP).


• Experience in a consulting or client-facing role.