- Model Lifecycle Management : Design, execute, and manage the complete lifecycle of LLMs, including model selection, domain-specific training, and fine-tuning techniques (e.g., LoRA, QLoRA) for optimal performance on enterprise applications.

- RAG System Implementation : Architect and implement robust Retrieval-Augmented Generation (RAG) pipelines to leverage proprietary and enterprise knowledge bases, enabling LLMs to provide context-aware, accurate, and up-to-date responses.

- AI Workflow Development : Utilize modern LLM orchestration frameworks such as LangChain, LangGraph, and similar tools to construct complex, modular, and production-ready AI workflows and agents.

- Vector Database Management : Develop efficient document ingestion and vectorization pipelines to process, index, embed, and manage enterprise knowledge bases using leading vector databases like Pinecone, FAISS, or Chroma.

- Prompt Engineering : Implement advanced prompt engineering, context optimization, and few-shot/zero-shot learning strategies to maximize LLM response quality, relevance, and safety.

AI/ML Engineering & Programming Excellence :

- Software Engineering : Write high-quality, modular, and maintainable code in Python, strictly adhering to strong software engineering principles, coding standards, and best practices.

- Data Pipeline Optimization : Build, optimize, and maintain efficient data pipelines for feature extraction, data preprocessing, and preparing data for both traditional machine learning models and LLM training/fine-tuning.

- ML Fundamentals : Apply deep understanding of deep learning and machine learning concepts for both traditional predictive modeling and advanced generative use cases.

- Scalability & Deployment : Design and implement scalable solutions, ensuring that LLM applications can handle high concurrency and integrate seamlessly into existing enterprise infrastructure.

Required Qualifications :

- Experience : [Specify required experience level, e.g., 5+ years] of professional experience in AI/ML Engineering, Data Science, or Software Development with a focus on Generative AI.

- Programming : Expert proficiency in Python and its relevant scientific and ML libraries (e.g., PyTorch, TensorFlow, NumPy, Pandas).

- LLM Ecosystem : Deep practical experience with open-source and proprietary LLMs (e.g., Llama, Mistral, GPT series) and techniques for model adaptation and deployment.

- Architecture : Proven experience implementing and deploying production-grade RAG systems and using orchestration frameworks like LangChain/LangGraph.

- Databases : Hands-on experience with vector databases (Pinecone, Chroma, FAISS) and embedding models.

- Cloud/DevOps : Experience with cloud platforms (AWS, GCP, or Azure) and containerization technologies (Docker, Kubernetes) for deploying AI/ML services is highly desirable.