Architect(Generative AI & LLM expert)

Role Summary:

As a Generative AI & LLM expert, you will support our AI and ML team in designing, developing, fine-tuning, and deploying large language models and generative AI applications. This is a unique opportunity to work on state-of-the-art AI technologies and enhance skills in machine learning, natural language processing, and deep learning.

Roles & Responsibilities

• Architect robust systems to integrate LLMs and support retrieval workflows.
• Provide guidance on the use of Vector DBs and model deployment on cloud
• Optimize the fine-tuning process for business-specific LLM use cases.platforms.
• Design application with on premise / cloud based LLM , RAG, Langchain.

Key Skills

• Model Training & Fine-Tuning: Assist/Build in training and fine-tuning large language models (e.g., GPT, LLaMA) on domain-specific data to improve model accuracy and relevance.
• Data Preparation & Preprocessing: Work with large datasets, perform data cleaning, tokenization, and prepare text data for model training and evaluation.
• Prompt Engineering: Experiment with and refine prompt techniques for various generative AI applications (e.g., text summarization, question answering, chatbots).
• Model Evaluation & Optimization: Help in evaluating models, using metrics such as BLEU, ROUGE, and perplexity, and work to optimize models for performance and accuracy.
• Collaborate with Cross-functional Teams: Work closely with engineering and product teams to understand project requirements, and contribute to developing scalable AI solutions.
• Documentation & Reporting: Document processes, model architectures, and code; assist in creating model cards and writing reports for stakeholders.
• Managing and training LLM models (e.g., fine-tuning llama3.1).
• Generating embeddings and managing semantic search via Vector DBs.