Mediabistro logo
job logo

Applied Scientist II: LLM Benchmarking for E-commerce

Socket.dev · Palo Alto, CA, USA ·

Pay:
171.600 - 222.200
Job type:
Full Time

Amazon.com Services LLC in Palo Alto, CA is seeking a researcher/engineer to design benchmarking and evaluation frameworks for Large Language Models in shopping applications. You will curate training data to improve model performance and work with scientists, engineers, and TPMs to push the boundaries of AI in ecommerce.
The role emphasizes building scalable benchmarks, publishing results, and contributing to core product challenges in a fast-paced environment.

#J-18808-Ljbffr