In today's fast-paced digital world, understanding customer feedback is more crucial than ever. Our cutting-edge solutions harness the power of Natural Language Processing (NLP) and Large Language Models (LLMs) to transform unstructured text into actionable insights.

As a Machine Learning Engineer on the Rewards and Loyalty Product team, you will leverage NLP techniques and LLM orchestration frameworks to transform customer feedback into actionable insights. You will have the opportunity to work with GenAI services and explore RAG architecture and Agentic AI concepts, ensuring we deliver top-notch solutions with your strong Python skills and experience in data processing libraries.

Job Responsibilities:

Develop and maintain NLP/LLM pipelines to extract and classify customer feedback using custom taxonomies.Write effective prompts and apply large language models (LLMs) to categorize and summarize unstructured text.Collaborate on taxonomy development for complaint categorization and feedback analysis.Implement and optimize topic modeling techniques to uncover emerging themes.Explore and prototype use cases for GenAI across various business domains.Integrate LLM frameworks and APIs using tools such as LangChain, LangGraph, and AWS Bedrock.Experiment with Claude, OpenAI, and other foundational models to build intelligent assistants.Support RAG (Retrieval-Augmented Generation) and Agentic AI workflows in early-stage initiatives.

 

Required qualifications, capabilities and skills:

Strong hands-on experience with NLP techniques (NER, topic modeling, text classification, etc.)Experience with LLM orchestration frameworks (LangChain, LangGraph, etc.)Exposure to GenAI services such as AWS Bedrock or Azure OpenAIStrong Python skills and experience with data processing libraries (Pandas, spaCy, HuggingFace, etc.)

 

Preferred qualifications, capabilities and skills:

Experience working with customer experience data, complaints, or survey analyticsFamiliarity with prompt engineering and working with LLMs (OpenAI, Claude, etc.)Working knowledge of RAG architecture and Agentic AI concepts is a plus