Applied Scientist I, Corp - CS - CET - SSA - Girish Subramanian

The Customer Engagement Technology team leads AI/LLM-driven customer experience transformation using task-oriented dialogue systems. We develop multi-modal, multi-turn, goal-oriented dialog systems that can handle customer issues at Amazon scale across multiple languages. These systems are designed to adapt to changing company policies and invoke correct APIs to automate solutions to customer problems. Additionally, we enhance associate productivity through response/action recommendation, summarization to capture conversation context succinctly, retrieving precise information from documents to provide useful information to the agent, and machine translation to facilitate smoother conversations when the customer and agent speak different languages.

Key focus areas include:

1. Task-Oriented Dialog Systems: Building reliable, scalable, and adaptive LLM-based agents for understanding intents, determining eligibilities, making API calls, confirming outcomes, and exploring alternatives across hundreds of customer service intents, while adapting to changing policies.
2. Lifelong Learning: Researching continuous learning approaches for injecting new domain knowledge while retaining the model's foundational abilities and prevent catastrophic forgetting.
3. Agentic Systems: Developing a modular agentic framework to handle multi domain conversations through appropriate system abstractions.
4. Complex Multi-turn Instruction Following: Identifying approaches to guarantee compliance with instructions that specify standard operating procedures for handling multi-turn complex scenarios.
5. Inference-Time Adaptability: Researching inference-time scaling methods and improving in-context learning abilities of custom models to enable real-time adaptability to new features, actions, or bug fixes without solely relying on retraining.
6. Context Adherence: Exploring methods to ground responses in specific customer attributes, account information, and behavioral data to prevent hallucinations and ensure high-fidelity responses.
7. Policy Grounding: Investigating techniques to align bot behavior with evolving company policies by grounding on complex, unstructured policy documents, ensuring consistent and compliant actions.
1. End to End Dialog Policy Optimization: Researching alignment approaches to optimize successful dialog completions.
2. Scalable Evaluations: Developing automated approaches to evaluate quality of experience, and correctness of agentic resolutions

Key job responsibilities
1. Research and development of LLM-based chatbots and conversational AI systems for customer service applications.
2. Design and implement state-of-the-art NLP and ML models for tasks such as language understanding, dialogue management, and response generation.
3. Collaborate with cross-functional teams, including data scientists, software engineers, and product managers, to integrate LLM-based solutions into Amazon's customer service platforms.
4. Develop and implement strategies for data collection, annotation, and model training to ensure high-quality and robust performance of the chatbots.
5. Conduct experiments and evaluations to measure the performance of the developed models and systems, and identify areas for improvement.
6. Stay up-to-date with the latest advancements in NLP, LLMs, and conversational AI, and explore opportunities to incorporate new techniques and technologies into Amazon's customer service solutions.
7. Collaborate with internal and external research communities, participate in conferences and publications, and contribute to the advancement of the field.