Pavan
Chauhan
Pavan Chauhan —Machine Learning Engineer based in Los Angeles.
Pavan Chauhan
—Machine Learning Engineer
based in Los Angeles.
Skills
Hey, Pavan here. I'm a Machine Learning Engineer based in Los Angeles. I build production-ready AI systems that transform complex research into efficient, real-world applications & websites—enjoying life all the while.
Whether you're looking to deploy a cutting-edge research model or build an efficient, data-driven product, I specialize in bridging the gap — from concept to production. Let's build something impactful.
End-to-End Model Development
Architecting and implementing advanced Transformer and CNN-RNN models for complex Computer Vision and NLP tasks, achieving state-of-the-art results in areas like American Sign Language recognition and bioacoustic analysis.
Edge AI & Performance Optimization
Specializing in model quantization and deployment using TensorFlow Lite, achieving real-time performance (up to 112 FPS) on resource-constrained edge devices like NVIDIA Jetson Nano and Apple M1.
MLOps & Scalable Deployment
Building robust, production-grade ML systems using Docker, FastAPI, and GitHub Actions for CI/CD. Experience in load-testing services to handle 1,000+ RPS and ensuring code quality with high test coverage (85% with PyTest).
Data Engineering & ETL Pipelines
Expertise in creating and optimizing data pipelines for large-scale datasets (3M+ rows) using Pandas and Spark. Proven ability to reduce ETL job runtimes by over 20% through vectorization and efficient processing techniques.
Applied AI Research & Innovation
Authored and presented two peer-reviewed research papers at international conferences (ADCIS & ICDSNS 2024). Passionate about translating novel concepts like Liquid Neural Networks and Nyströmformers into practical, high-impact solutions.
Interactive ML Prototyping
Developing full-stack applications with React/Next.js and Flask to create intuitive, interactive demos for machine learning models, effectively showcasing their real-world capabilities to stakeholders.
Work Experience
Dec 2024 - Apr 2025
CHARUSAT
Research & Development Intern — Senior Capstone
Designed SignEase, a landmark-aware Transformer that hits 98.3% top-1 across 250 ASL classes and streams in real time (156 ms desktop | 476 ms mobile). Quantized & TFLite-deployed the model: 78 FPS Apple M1 and 112 FPS NVIDIA Orin Nano—opening the door to fully offline accessibility apps.
Python
TensorFlow/Lite
MediaPipe
CUDA
React/Next.js
Flask
Jul 2023 - Jun 2024
CHARUSAT
Research Intern
Led model-workstream for Kaggle "Isolated Sign-Language Recognition" (100k videos, 250 signs): reached 81% top-1 (+10 pp) and kept 30 FPS on-device with TFLite. Presented the work at ADCIS 2024 (220+ attendees); publication later cited by two external research groups. Mentored two juniors on data-augmentation tricks that shaved 20% off training wall-time.
Python
TensorFlow
MediaPipe
Parquet
CUDA
May 2023 - Jun 2023
CHARUSAT
Development & Research Intern
Refactored a legacy Pandas pipeline into vectorised operations, trimming a 3M-row ETL job 25 min → 19 min (-24%). Containerised a FastAPI inference service and soak-tested it to 1,000 req/s @ 110 ms P95 on AWS EC2. Wrote 40+ PyTest cases (85% coverage), introduced GitHub Actions CI, and documented a new REST contract for the ASL API.
Python
Pandas
FastAPI
AWS EC2
Docker
PyTest
A little about me.
.png)
I am a Machine Learning Engineer based in Los Angeles, CA with 2 years of experience building CV and NLP models that have achieved significant performance improvements. Currently pursuing my M.S. in Computer Science at Cal State LA, I specialize in developing scalable ML solutions using Python, TensorFlow, PyTorch, and cloud technologies. My expertise spans from research to production, with published papers in ADCIS 2024 and ICDSNS 2024, hands-on experience with edge deployment on Jetson devices.
When I’m not training models, I enjoy listening music, swimming, and playing soccer. I'm passionate about the intersection of AI research and real-world applications, always curious to explore new architectures and push the boundaries of what's possible with machine learning.
FAQ
What types of ML projects do you specialize in?
I specialize in Computer Vision (ASL recognition, image classification), NLP (text analysis, language models), edge AI deployment (TensorFlow Lite, NVIDIA Jetson), and production ML systems with end-to-end deployment pipelines.
How do you ensure model performance in production?
I implement comprehensive testing with 85%+ test coverage using PyTest, load testing for 1000+ RPS, model quantization for edge deployment, and continuous monitoring. All projects include detailed documentation and deployment guides.
Can you work with existing ML models or datasets?
Absolutely! I can optimize existing models, fine-tune pre-trained models, work with your datasets to improve performance, and help deploy research models into production environments. I also provide model migration and performance optimization services.
What's your typical project timeline and process?
Projects typically range from 2-8 weeks depending on complexity. My process includes: initial consultation, data analysis, model development, testing & validation, deployment, and documentation. I provide weekly progress updates and maintain clear communication throughout.