Description

You will design and develop end-to-end Retrieval-Augmented Generation (RAG) solutions and advanced AI chatbot applications.

Responsibilities

• Design, develop, and fine-tune LLMs specifically for RAG implementation.
• Lead experimentation with different chunking and retrieval methods to improve system effectiveness.
• Develop, train, and optimize language models using PyTorch and TensorFlow.
• Conduct performance evaluations focusing on model accuracy and bias identification.
• Manage high availability and deployment of cloud-native applications and on-premises LLM hosting.

Required Skills

• 10+ years of proficiency in Python.
• 5+ years of experience in Machine Learning and AI.
• 5+ years of experience with GenAI Foundation Models and Vector DB (including multi-vector).
• 5+ years of experience in RAG and Model Fine-Tuning.
• Expertise in OpenAI, Google Vertex, or Hugging Face models.
• Experience with orchestration tools such as LangChain or Semantic Kernel.
• Hands-on experience with PySpark, PyTorch, TensorFlow, and Streamlit.
• Knowledge of GitOps principles and tools like Git, Tekton, Flux, or ArgoCD.

Preferred Skills

• Experience with Prompt Engineering and AI Chatbot development.
• Experience facilitating the adoption of Unstructured APIs.

Key Skills

Education

Bachelor's degree in Computer Science