LLM Engineer

Total: 1+ Years to 4 plus years

Relevant: 1+ Years 

1. Proficiency in PyTorch, TensorFlow, or similar frameworks for natural language processing.
2. Understanding of Large Language Models (LLMs), transformers, attention mechanisms.
3. Experience with open-source LLMs
4. Knowledge in developing RAG-based pipelines using frameworks like LangChain & LlamaIndex.
5. Knowledge of deploying LLMs on cloud-based GPUs, with optimization for cost and latency.
6. Working knowledge of the engineering components essential in a Gen AI application, including Vector DB, caching layer, chunking, and embedding

1. Understanding of NLP techniques and embedding retrieval for efficient information retrieval and response generation.
2. Hands-on experience with Hugging Face models, and application of LangChain and LlamaIndex frameworks.
3. Skills in implementing agentic approaches to optimize LLM interaction and task completion in conversational AI.

1. Assist in implementing agentic approaches to optimize the interaction of large language models in automated and interactive AI solutions.
2. Contribute to analysing model performance using basic NLP evaluation metrics and help refine prompts and fine-tuning strategies under guidance.
3. Support the deployment of fine-tuned models on cloud infrastructure, focusing on ensuring reliability and meeting project requirements.
4. Collaborate with senior data scientists and engineers to implement NLP solutions, gaining hands-on experience in maintaining high-performance AI systems.