Headline

Generative AI | Speech × Vision | Deep Learning | Open Source

About

I work at the intersection of speech, vision, and generative AI—training deep learning models, designing large-scale data pipelines, and shipping production-ready models. From raw audio to expressive, high-fidelity avatars, I focus on turning cutting-edge research into scalable, real-world systems.

Location

Delhi

Work experience

Research Engineer at Sarvam, Jan 2026 - Present · 11 mos

Research Engineer - Deep Learning at Gan.AI, Jan 2023 - Jan 2026 · 3 yrs 1 mo, Delhi, India

Senior Data Scientist at Thoughtworks, Feb 2019 - Jan 2023 · 4 yrs, India

Researcher at Freie Universität Berlin, Nov 2015 - Feb 2018 · 2 yrs 4 mos, Berlin Area, Germany, Computational Biophysics Worked on developing molecular dynamics simulations techniques to better understand hydration interaction between lipid membranes.

Research Assistant at University of Calgary, May 2012 - Aug 2012 · 4 mos, Calgary, Canada Area, Initiative sponsored by Mitacs Globalink program (www.mitacs.ca/globalink). Selected among top students from India, Brazil, China and Mexico. Worked on developing better finite difference schemes for the 2D acoustic wave equation. Received a letter of appreciation from the honourable Prime Minister of Canada for the same.

Education

Master of Science (M.S.), Computational Physics, Freie Universität Berlin

Master of Science (M.S.), Engineering Physics/Applied Physics, Gdańsk University of Technology