Requirements
What You'll Do:
• Work on interesting client projects, implementing explainability frameworks (RAGAS) for AI model outputs
• Build RAG (Retrieval -Augmented Generation) systems for geoscience document automation
• Fine -tune open -source LLMs using LoRA/QLoRA for domain -specific NLP applications
• Design and implement embedding pipelines and vector database architectures to support enterprise knowledge management
• Assist in optimizing LLM performance for accuracy, latency, and cost efficiency
• Participate in system architecture reviews to ensure scalable, secure, and production -ready LLM deployment
• Document experiments, model configurations, and evaluation results
Requirements:
• MTech / MSc in NLP, AI/ML, or related field (current student or recent grad)
• Strong Python skills and experience with Transformers library (Hugging Face)
• Academic project experience with LLMs, fine -tuning, or NLP tasks
• Understanding of modern LLM techniques (prompt engineering, RAG, fine -tuning)
• Bonus: Experience with vector databases, embedding models, or LLM serving (vLLM, Ollama)What You'll Learn
• Production LLM deployment for offshore wind sector clients
• RAG architecture for enterprise geoscience knowledge management
• LLM evaluation and quality control (RAGAS, human -in -the -loop validation)
• AI systems architecture for LLM deployment under Technical Architect mentorship
What You'll Learn:
• Production LLM deployment for offshore wind sector clients
• RAG architecture for enterprise geoscience knowledge management
• LLM evaluation and quality control (RAGAS, human -in -the -loop validation)
• AI systems architecture for LLM deployment under Technical Architect mentorship