Design and implement sophisticated Large Language Model (LLM)-powered systems, focusing on context engineering, agentic workflows with tool integration, and scalable serving infrastructure to power next-generation features.

Lead the development of evaluation frameworks, including the creation of high-quality datasets and automated auto-rater solutions, to identify model weaknesses and drive performance improvements.

Collaborate closely with Product, User Experience (UX), and Research teams to translate user needs into intuitive features, ensuring a seamless integration of Artificial Intelligence (AI) capabilities within the ecosystem.

Analyze user data and model outputs to refine personalized experiences, partnering with Research teams to feed product-driven insights back into base model development for continuous enhancement.

Advocate a culture of excellence by defining performance metrics, setting development standards, and establishing best practices for Large Language Model (LLM) evaluation and ethical, responsible AI deployment.

Bachelor’s degree or equivalent practical experience.

2 years of experience with software development programming in Python.

2 years of experience working with Large Language Models (LLMs), including fine-tuning, prompt engineering, or evaluating LLM performance.

2 years of experience with performance optimization, systems data analysis, visualization tools, or debugging.