Description
You will build and optimize generative AI solutions using large language models and natural language processing techniques.
Responsibilities
- Implement agentic approaches to optimize LLM interaction in automated and interactive AI solutions.
- Analyze model performance using NLP evaluation metrics and refine prompts and fine-tuning strategies.
- Deploy fine-tuned models on cloud infrastructure, ensuring reliability and meeting project requirements.
- Collaborate with senior engineers to implement and maintain high-performance NLP systems.
Required Skills
- 1 to 4+ years of total experience with at least 1 year of relevant experience.
- Proficiency in PyTorch, TensorFlow, or similar frameworks for natural language processing.
- Deep understanding of Large Language Models (LLMs), transformers, and attention mechanisms.
- Hands-on experience with open-source LLMs and Hugging Face models.
- Experience developing RAG-based pipelines using LangChain and LlamaIndex.
- Knowledge of engineering components including Vector DB, caching layers, chunking, and embedding.
- Ability to deploy LLMs on cloud-based GPUs with optimization for cost and latency.
- Background in NLP, AI/ML, and implementing agentic approaches for conversational AI.
- BE/B.Tech or ME/M.Tech degree.
Preferred Skills
- Understanding of NLP techniques and embedding retrieval for efficient information retrieval.
- Experience implementing agentic workflows to optimize task completion.