AI Model Test, Evaluate, Validate, Verify: Design and conduct systematic tests to evaluate AI model safety, security, and performance. This includes researching and applying various security/safety test domains, industry benchmarks, and advanced evaluation methodologies (e.g., benchmark based evaluations, LLM-as-a-Judge, etc).
Design and develop AI productivity tools for internal engineering teams, such as coding assistants, knowledge retrieval systems, and workflow automation tools
Reimagine and enhance core ITSM practices (Incident, Problem, Change, and Knowledge Management) using modern development frameworks and automation tools.
Enhance Enterprise Security Architecture: Continuously assess and improve the organization’s cybersecurity architecture to address evolving threats and emerging technologies.
Advise AWS customers on how to increase their speed of AI innovation, the efficiency of their IT, and the business value their technology generates by adopting cloud technology from a people, process and technology perspective.
Domain Authority: Serve as the semiconductor domain expert for the Eureka Materials Agent, ensuring technical accuracy and industrial practicability for chip, device, and material reverse engineering scenarios.
Build core Agent logic, including but not limited to task planning and orchestration, tool calling, multi-turn dialogue management, memory, RAG, context engineering, and multi-agent collaboration.
Large language Model Algorithm Development: Build domain-specific large language models (LLM/MLLM) for e-commerce, integrating domain knowledge to rapidly apply models to business scenarios.
Responsible for using algorithms to mine, identify, and predict risks and low-quality merchants, products, and creators in e-commerce scenarios, and assist businesses in managing and controlling them.