AI Fine Tuning Expert

Role Overview: As an AI Fine Tuning Expert at our company located in Siruseri, Chennai, your primary responsibility will be to fine-tune LLaMA models on domain-specific data such as finance, healthcare, telecom, legal, etc. You will also be involved in curating, cleaning, and pre-processing datasets for supervised and unsupervised fine-tuning. Additionally, you will implement low-rank adaptation (LoRA), PEFT, QLoRA, or full fine-tuning as required and optimize model training performance using tools/libraries. Evaluating fine-tuned models using appropriate metrics, deploying and integrating models with APIs, RAG pipelines, or inference servers, and conducting safety audits and hallucination checks post-fine-tuning will also be part of your responsibilities. Furthermore, you should be familiar with open-source LLMs beyond LLaMA (Mistral, Falcon, Mixtral, etc.), hands-on with orchestration tools like LangChain, LangGraph, CrewAI, or Flowise, and have knowledge of tokenizers, embeddings, and prompt templates. Proficiency in Python, PyTorch, and model training workflows is essential for this role. Key Responsibilities: - Fine-tune LLaMA models on domain-specific data - Curate, clean, and pre-process datasets for supervised and unsupervised fine-tuning - Implement low-rank adaptation (LoRA), PEFT, QLoRA, or full fine-tuning as per need - Optimize model training performance using tools/libraries - Evaluate fine-tuned models using appropriate metrics - Deploy and integrate models with APIs, RAG pipelines, or inference servers - Use tools like Weights & Biases, LangSmith, or TensorBoard for training monitoring and logging - Conduct safety audits and hallucination checks post-fine-tuning - Familiarity with open-source LLMs beyond LLaMA (Mistral, Falcon, Mixtral, etc.) - Hands-on with orchestration tools like LangChain, LangGraph, CrewAI, or Flowise - Knowledge of tokenizers, embeddings, and prompt templates - Experience with LLaMA (preferably LLaMA 2 / LLaMA 3) and Hugging Face ecosystem - Proficiency in Python, PyTorch, and model training workflows Qualifications Required: - Deep expertise in Fine tuning in LLama, LoRA, QLoRA - Strong command of Python & ML Libraries Please note that the company offers the following benefits: - Work with Top tier AI minds - Access to high-performance infra for model training - Opportunity to drive innovation with real-world applications - Be part of a growing AI team building next-gen tools - Continuous learning and innovation - Competitive salary with growth opportunities,