Generative AI Engineer - NLP / LLM

Key Responsibilities :

• Develop and fine-tune LLMs for classification, NLP, and generative AI use cases.
• Build RAG pipelines with vector databases and implement prompt engineering strategies.
• Conduct data preprocessing for LLM training including tokenization and embedding generation.
• Design custom chatbots, text generation, and document analysis solutions.
• Implement LLM evaluation metrics (BLEU, ROUGE, perplexity) and human feedback loops.
• Deploy conversational AI and content generation models in Requirements :
• 2 years hands-on LLM development (GPT, BERT, T5, Llama, Claude).
• Proficient in Transformers, Hugging Face, LangChain, OpenAI API.
• Experience with vector databases (Pinecone, Weaviate, ChromaDB) and semantic search.
• Strong Python, SQL, and deep learning (PyTorch, TensorFlow).
• Knowledge of fine-tuning techniques (LoRA, QLoRA, PEFT) and model quantization.
• Understanding of prompt engineering, chain-of-thought, and few-shot learning.
• Familiarity with MLOps for LLMs (model versioning, A / B testing, monitoring)

(ref : hirist.tech)