As a Generative AI & NLP Developer (Python/LLMs), you will design, build, and deploy LLM-powered and NLP-driven applications. You will focus on text processing, extraction, summarization, conversational AI, and retrieval-augmented generation (RAG) solutions. Your expertise in Python, LLM frameworks, NLP pipelines, and vector databases will be critical in delivering scalable, production-grade AI applications for enterprise use cases.

Develop and deploy NLP and GenAI applications: text extraction, summarization, chatbots, document intelligence, and knowledge assistants. Build Python APIs and services (Flask/FastAPI) to integrate LLM/NLP models into enterprise workflows. Implement embedding-based retrieval and semantic search using vector databases (FAISS, Pinecone, Weaviate, Milvus). Work with LLM and NLP frameworks (Hugging Face Transformers, LangChain, LlamaIndex, SpaCy, NLTK) for fine-tuning and orchestration. Optimize pipelines for scalability, accuracy, and performance. Collaborate with engineering teams to ensure smooth integration into production environments.

Must-Have Technical Skills Expert in Python programming: OOP, APIs, data structures, concurrency. Strong experience with NLP frameworks (Hugging Face, SpaCy, NLTK, Transformers). Practical expertise in text extraction, preprocessing, and information retrieval. Hands-on with LLMs and GenAI tools: Hugging Face, LangChain, LlamaIndex. Knowledge of vector databases: FAISS, Pinecone, Weaviate, Milvus. Familiarity with Pandas/NumPy for data wrangling and preprocessing. Nice-to-Have Technical Skills Exposure to TensorFlow / PyTorch for fine-tuning. Understanding of MLOps (Docker, Kubernetes, CI/CD). Experience with cloud platforms (AWS, Azure, GCP).