Generative AI Engineer - LLM/RAG

Job Title : Generative AI Engineer LLM | AWS & Azure | RAG

Experience : 5 to 8 Years

Location : Pune, Bangalore, Hyderabad, Chennai, Gurugram, Jaipur

Job Type : Full-time / Permanent

Work Mode : Hybrid / Remote Flexibility (as per business requirement)

Job Description :

We are seeking a passionate and experienced Generative AI Engineer to join our growing AI/ML team. The ideal candidate will have hands-on experience in designing, building, and deploying LLM-based solutions with a strong focus on Retrieval-Augmented Generation (RAG). You should be comfortable working across AWS and Azure platforms, leveraging cloud-native AI/ML services to deliver scalable and secure solutions.

Key Responsibilities :

- Design and develop generative AI models and pipelines using Large Language Models (LLMs) like GPT, LLaMA, Claude, or similar.

- Implement and optimize RAG (Retrieval-Augmented Generation) pipelines using vector databases and search engines (e.g., FAISS, Weaviate, Pinecone, Azure Cognitive Search).

- Fine-tune and customize open-source or commercial LLMs for specific domain needs.

- Deploy AI/ML models using AWS SageMaker, AWS Lambda, ECS/EKS, and Azure ML Studio / Azure AI services.

- Integrate AI models into enterprise systems using APIs, microservices, and serverless architectures.

- Ensure solutions are scalable, secure, and optimized for performance across cloud environments.

- Collaborate with product managers, data scientists, and MLOps teams for full lifecycle model development and deployment.

Must-Have Skills :

- LLM experience : Prompt engineering, fine-tuning, or customization of LLMs (e.g., OpenAI, Hugging Face Transformers).

- RAG Implementation : Knowledge of semantic search, embeddings (e.g., OpenAI, BERT), vector stores (e.g., FAISS, Pinecone).

Cloud Platforms :

- AWS : SageMaker, Lambda, API Gateway, IAM, EKS/ECS.

- Azure : Azure ML Studio, Azure OpenAI, Azure Cognitive Search, Azure Functions.

- Strong Python programming skills (e.g., LangChain, Transformers, PyTorch, or TensorFlow).

- Experience with MLOps, CI/CD pipelines for model deployment.

- Strong understanding of data privacy, security, and compliance in AI systems.

Preferred Skills :

- Hands-on with tools like LangChain, LlamaIndex, or similar.

- Experience in deploying