Description

You will design and develop end-to-end Retrieval-Augmented Generation (RAG) solutions to achieve high-quality results on client data.

Responsibilities

• Design, develop, and optimize language models using PyTorch and TensorFlow.
• Lead experimentation with different chunking and retrieval methods to enhance RAG system efficiency.
• Develop, train, and fine-tune LLMs specifically for RAG applications.
• Conduct performance evaluations focusing on model accuracy and bias identification.
• Collaborate with cross-functional teams to integrate AI solutions into enterprise applications.

Required Skills

• 10+ years of proficiency in Python.
• 5+ years of experience in Machine Learning, AI, and Automated Artificial Intelligence tools.
• 5+ years of experience with GenAI Foundation Models, Vector DB (multi-vector), and RAG.
• 5+ years of experience with AWS, Azure, and other cloud platforms.
• 5+ years of experience with Docker and Kubernetes.
• Expertise in Langchain, Semantic Kernel, PySpark, and Streamlit.
• Experience with OpenAI, Google Vertex, or Hugging Face models.
• Proficiency in Prompt Engineering and AI chatbot development (QA, translation, search, and summarization).
• Experience with GitOps tools such as Git, Tekton, Flux, or ArgoCD.

Preferred Skills

• Experience managing infrastructure and application deployments using GitOps principles.

Key Skills

Education

Bachelor's