Neda K.

Llm Benchmarking Specialist @Turing

Irvine, CA, US
MOBILE NUMBERS
+91 *********19

Signup · Get unlimited contacts

WORK HISTORY

Jan 2025 — Present

Llm Benchmarking Specialist @Turing

View department →

US

Design headroom-level benchmarks and adversarial prompts for evaluating clinical and biological reasoning in LLMs.• Lead multimodal evaluation projects (text, image, and image-code) including CUJ, HLE, and ICE pipelines.• Collaborate with engineering and validation teams to refine rubrics, safety criteria, and model debugging workflows.• Provide medical domain expertise (MD, PhD) to ensure clinical accuracy and safety alignment.

EDUCATION

1990 — 1992

Universitat Autònoma de Barcelona

Postgraduate Degree, Fellowship in Dermatology

N/A

University of Bedfordshire

Bachelor of Science - BS, Biomedical/Medical Engineering

N/A

Universidad Autónoma de Madrid

Master of Business Administration - MBA, Human Resources Management/Personnel Administration, General

1986 — 1990

UCLA

Doctor of Medicine - MD

1992 — 1995

Universidad Autónoma de Madrid

Postgraduate Degree, Fellowship in Reconstructive Surgery

ABOUT NEDA K.

I am an MD and PhD with more than 20 years of international clinical, academic, and executive leadership experience across Europe, the Middle East, and the United States. My career spans trauma and emergency medicine, dermatology, reconstructive surgery, academic teaching, and large-scale R&D program management.In recent years I transitioned into advanced AI and LLM evaluation, where I design, review, and lead complex multimodal benchmark systems for biology, medicine, and safety analysis. At Turing, I develop headroom-level questions, adversarial prompts, and evaluation frameworks used to assess clinical reasoning, hallucination risks, and image-code generation in frontier large language models.I previously built and operated multiple clinical practices, served as a professor of pathology and emergency medicine, and directed major R&D initiatives. I have led multidisciplinary teams, delivered international healthcare projects, and worked with UN-affiliated organizations in humanitarian medicine.I bring deep medical expertise, research training, and executive experience to AI teams focused on safe, accurate, and clinically aligned model development.I have hands-on experience with Python, JSON structuring, HTML-based image-code evaluation, and modern LLM workflows, allowing me to collaborate effectively with engineering teams and contribute to advanced model debugging, safety assessment, and evaluation design.

This profile is compiled from publicly available professional sources. Unifers is not affiliated with or endorsed by LinkedIn. Request removal of this profile.