Generative AI, LLM Engineer

Job Title : Generative AI, LLM Engineer

Experience : 5-10 Years

Location : Chennai

Roles & Responsibilities

Design, build, and deploy production-ready Generative AI and LLM solutions

Develop end-to-end GenAI pipelines: data collection → preprocessing → model training → evaluation → deployment

Implement LLMs and multimodal AI models using frameworks like LangChain, LlamaIndex, or OpenAI APIs

Conduct RAG (Retrieval-Augmented Generation) implementations for enterprise use cases

Optimize model inference for cost efficiency and low latency

Collaborate with cross-functional teams (data science, product, engineering) to design intelligent AI applications

Integrate AI models into production systems and ensure scalability

Stay current with the latest AI research, tools, and frameworks

Requisites

Strong Python programming skills

Hands-on experience with PyTorch or TensorFlow

Experience with LLMs (GPT, Claude, LLaMA, Mistral) and open-source libraries (LangChain, Hugging Face Transformers)

Knowledge of prompt engineering, embeddings, and vector databases (FAISS, Pinecone, Weaviate, Milvus)

Familiarity with cloud platforms (Azure preferred, AWS or GCP acceptable)

Experience with API development, Docker, Kubernetes, and CI/CD pipelines

Exposure to diffusion/image generation models (Stable Diffusion, DALL·E) and multimodal AI systems

Understanding of MLOps best practices and AI production deployment