Santhiya A
@santhiyaa
Applied Scientist at Microsoft Edge who compressed a production model by 88% and cut inference latency 2.2x.
IndiaWhat I'm looking for
At Microsoft Edge, I compressed a production ML model by 88% and cut inference latency 2.2x with no loss in precision or recall. I also fine-tuned and deployed a 10-language model that reached 83% accuracy, within four points of the English baseline.
I built RAG and vector search pipelines, and used active learning to reduce labeled-data needs by 75%. My work also includes automated evaluation and Responsible AI guardrails, plus C++ features in the Chromium (Edge) codebase.
Experience
Work history, roles, and key accomplishments
Reduced a production ML model by 88% and inference latency by 2.2x with zero loss in precision/recall. Architected RAG pipelines, fine-tuned a 10-language LLM, and built evaluation and Responsible AI guardrails.
Restructured telemetry payloads for Edge notifications, improving feature-team visibility and debugging efficiency.
Research Intern
Payoda Technologies
Mar 2022 - Oct 2022 (7 months)
Built an end-to-end Named Entity Recognition and Relation Extraction pipeline for financial text, modeling and querying entities in Neo4j.
Education
Degrees, certifications, and relevant coursework
Sri Krishna College of Engineering and Technology
B.Tech, Artificial Intelligence & Data Science
2020 - 2024
Grade: 9.20/10.0
Pursued a B.Tech in Artificial Intelligence & Data Science, achieving a CGPA of 9.20/10.0.
Tech stack
Software and tools used professionally
Availability
Location
IndiaAuthorized to work in
Salary expectations
Social media
Interested in hiring Santhiya?
You can contact Santhiya and 90k+ other talented remote workers on Himalayas.
Message SanthiyaGet matched with your dream remote job
Sign up now and join over 250,000+ remote workers who receive personalized job alerts, curated job matches, and more for free!
