I am a Senior Research Scientist at Netflix, working on multimodal LLMs, post-training, and evaluation for translation, dubbing, and subtitling.
I develop reward models and human-calibrated evaluation systems to improve model quality. My work connects multimodal research with production systems that help bring stories to audiences across languages.
My doctoral research focused on multimodal contrastive learning, deep metric learning, and deep feature fusion. My Ph.D. was funded by the IARPA BRIAR, NSF AI Institute, Qualcomm, NSF CITeR, NSF DiBBS, and NSF S&CC programs.
News
August 2026: Promoted to Senior Research Scientist at Netflix.
Nov 2025: I am hiring a Research Intern for summer 2026 at Netflix Research. Reach out if you are interesed.
Nov 2025: Serving as an Area Chair for ICASSP 2026
Feb 2025: Glad to share that I have joined Netflix Research as full-time Research Scientist
Nov 2024: Glad to share that I our paper at Netflix Research - "RSMS: Audio-Visual Representation Learning For Lip-Sync
Estimation Through Ranking Augmented Contrastive Training" was accepted at ICASSP 2025
Oct 2024: Glad to share our paper 'ProxyFusion: Face Feature Aggregation Through Sparse Experts' got accepted at NeurIPS 2024
August 2024: Glad to share our paper 'SCOT: Self-Supervised Contrastive Pre-training For Zero-Shot Compositional Retrieval' got accepted at WACV 2025 in Round 1 (12.1% Acceptance Rate)
May 2024: Started summer internship at Netflix Research as a Research Scientist.
Dec 2023: Honored to receive the Graduate Leadership Award, from Department of Computer Science, University at Buffalo
Feb 2024: Glad to share our paper 'GestSpoof: Gesture Based Spatio-Temporal Representation Learning For Robust Fingerprint Presentation Attack Detection.' got accepted at FG 2024
Dec 2023: Glad to share our paper 'Conditional Neural Aggregation Network For Unconstrained Long Range Person Feature Fusion' got accepted in IEEE TBIOM Journal
Sept 2023: CoNAN received the Best Paper Award at IJCB 2023. Link
July 2023: Glad to share our paper title: 'CoNAN - Conditional Neural Aggregation Network for Unconstrained face recognition' has been accepted at IJCB 2023.
May 2023: Started summer internship at Yahoo Research as a Research Scientist.
April 2023: Glad to share our paper 'RealCQA - Scientific Chart Question Answering as a Test-bed for First-Order Logic' got accepted at ICDAR 2023.
April 2023: Presented my work on spatio-temporal fingerprint spoof detection at CITeR-EAB workshop at Idiap, Switzerland.
Feb 2023: Honored as one of the winner of SEAS PhD Research Poster Award 2023, by School of Engineering and Applied Sciences, at University at Buffalo
Feb 2023: I will be co-organizing the IJCB LivDet 2023 Challenge on detecting contactless fingerprint spoofs.
Feb 2023: Our book chapter on Deep Metric Learning in Handbook Of Statistics is now available online.
Designed novel pre-training strategies and transformer architectures for large scale vision-language contrastive pretraining on 100M scale datasets. Evaluation on downstream tasks such as zero-shot image classification, text-image retrieval, object-detection etc.
I am Graduate Research Assitant (SUNY) at CUBS lab at University at Buffalo, State University of New York. I am working with Prof. Srirangaraj (Ranga) Setlur and Prof. Venu Govindaraju on an NSF funded project called Made@UB ML toolkit. ML Toolkit is an easy-to-use GUI based application, developed to reduce the time it takes to build prototypes for ML models as well as experiment with various feature extraction methods available.
At Persistent Systems we build software that drives the business of our customers; enterprises and software product companies with software at the core of their digital transformation.