Sanat Agrawal profile photo 1 on Tal

Sanat Agrawal

Researcher & Developer | IIT Bombay EE Dual ’27 | Research Intern @ Idiap, Switzerland | Founding Engineer @ Novare Talent | Semester Exchange @ EPFL | SURI ’24 @ ASU

Mumbai

2+ years of work experience

Novare Talent
Jul 20251 yr 2 mosPresent

Idiap Research Institute
Oct 20256 mosMar 2026

Hybrid

Proposed Concatenative Neural Speech Synthesis : a novel framework integrating Festival unit selection with WavLM SSL features for zero-shot multi-speaker TTS. Achieved +0.81 UTMOS gain over baseline using HiFi-GAN vocoding and spectral smoothing. Co-authored paper submitted to Interspeech 2026.
SalesAgents AI
Jun 20253 mosAug 2025

Arizona State University
May 20243 mosJul 2024

United States

Implemented a Physics-Informed Neural Network to estimate parametric uncertainties in DAB DC-DC converters (92% accuracy). Improved converter efficiency by 67% using adaptive loss-optimal control. Validated against real hardware data.
Student Alumni Relations Cell, IIT Bombay
Jun 20231 yr 1 moJun 2024

Working with a team of 80+ members organizing 40+ events to foster relations among 60k+ alumni and students Developed a registration portal for Mentors & Mentees of ASMP using HTML, CSS, JS, Bootstraps & Django Revamped the Nail The Prep (NTP) website by adding new styled Sections such as Testimonials and Alum Diaries, answering various Internship related queries, sharing Experience and providing Guidance for Preparation Optimized and Generated personalized yearbooks for 500+ users using React utilizing render-to-PDF functionality

Sanat’s AI Stack

claude code
claude code
claude
claude
codex
codex
cursor
cursor
opencode
opencode
claudecode
claudecode

Education

Indian Institute of Technology, Bombay

Dual degree, Electrical engineering

Indian Institute of Technology, Bombay

20225 yrs2027
EPFL

Semester Exchange, Electrical and Electronics Engineering

EPFL

20251 yr2026

Join Sanat and 10k+ other professionals on

Tal Boss

Tal is the app where bosses meet engineers & builders directly, without middlemen

Download Tal Boss

Sanat Agrawal on Tal

Headline

Researcher & Developer | IIT Bombay EE Dual ’27 | Research Intern @ Idiap, Switzerland | Founding Engineer @ Novare Talent | Semester Exchange @ EPFL | SURI ’24 @ ASU

About

I'm a final-year Electrical Engineering student at IIT Bombay (Dual Degree '27), and I spend most of my time doing two things I genuinely love : research and building, from speech AI systems to full-stack platforms that actually ship. On the research side, I'm currently working on Verbatim ASR for Indic languages as my Dual Degree Project- building systems that capture the full richness of natural speech (fillers, disfluencies, code-switching) rather than cleaning it away. Before this, I spent time at the Idiap Research Institute in Switzerland working on Neural Speech Synthesis, and at Arizona State University (SURI '24) applying Physics-Informed Neural Networks to power electronics. I also did a semester exchange at EPFL, Switzerland, where I worked on projects spanning automatic differentiation, facial recognition, and image processing. On the builder side, I'm a Founding Engineer at Novare Talent (incubated at SINE, IIT Bombay) — an AI-native hiring platform I helped build from scratch, now serving 2000+ candidates across 40+ internships. Previously at SalesAgent.ai, I worked on optimizing multilingual voice pipelines for real-time conversational AI. I'm drawn to problems where research and engineering genuinely intersect i.e where a good idea needs both rigorous thinking and clean execution to become real. sanat-agrwl.github.io | sanatagrwl@gmail.com

Location

Mumbai

AI stack

claude code

claude

codex

cursor

opencode

claudecode

Work experience

Founding Engineer at Novare Talent, Jul 2025 - Present · 1 yr 2 mos

Research Intern at Idiap Research Institute, Oct 2025 - Mar 2026 · 6 mos, Hybrid, Proposed Concatenative Neural Speech Synthesis : a novel framework integrating Festival unit selection with WavLM SSL features for zero-shot multi-speaker TTS. Achieved +0.81 UTMOS gain over baseline using HiFi-GAN vocoding and spectral smoothing. Co-authored paper submitted to Interspeech 2026.

AI and Systems Engineer at SalesAgents AI, Jun 2025 - Aug 2025 · 3 mos

Summer Research Intern at Arizona State University, May 2024 - Jul 2024 · 3 mos, United States, Implemented a Physics-Informed Neural Network to estimate parametric uncertainties in DAB DC-DC converters (92% accuracy). Improved converter efficiency by 67% using adaptive loss-optimal control. Validated against real hardware data.

Web Coordinator at Student Alumni Relations Cell, IIT Bombay, Jun 2023 - Jun 2024 · 1 yr 1 mo, Working with a team of 80+ members organizing 40+ events to foster relations among 60k+ alumni and students Developed a registration portal for Mentors & Mentees of ASMP using HTML, CSS, JS, Bootstraps & Django Revamped the Nail The Prep (NTP) website by adding new styled Sections such as Testimonials and Alum Diaries, answering various Internship related queries, sharing Experience and providing Guidance for Preparation Optimized and Generated personalized yearbooks for 500+ users using React utilizing render-to-PDF functionality

Education

Dual degree, Electrical engineering, Indian Institute of Technology, Bombay

Semester Exchange, Electrical and Electronics Engineering, EPFL

Public links

github: https://github.com/sanat-agrwl