Verified background and credentials
Abhik Sarkar is the Director of Machine Learning at Cloudastructure Inc, where he leads a globally distributed team that processes over 7 million videos per day at 98% accuracy for real-time threat detection. He has 8+ years of experience spanning computer vision, GPU optimization (CUDA, TensorRT, NVDEC pipelines), MLOps, and large-scale distributed systems for video processing.
- Current role
- Director, Machine Learning at Cloudastructure Inc
- Undergraduate degree
- Bachelor of Technology in Computer Science and Engineering, National Institute of Technology, Raipur
- Graduate coursework
- Introduction to High-Performance Computing, Indian Institute of Science, Bangalore
- Stanford coursework
- CS224W: Machine Learning with Graphs, Stanford Center for Professional Development
- Speaking history
- PyCon India 2024 and 2025, PyCon Japan 2024, BangPypers (Build with AI and December Meetup), DevFest 2023, KJ Somaiya Techfest 2019
- Publications
- Technical articles on GPU debugging (Xid 31 MMU faults), CUDA matrix multiplication, TensorRT, kernel fusion, video codecs at /articles
See also: /about for entity overview · /expertise for canonical pages by topic · /talks for conference slides · /papers for paper analyses · GitHub for open-source work.
Impact at Scale
Key metrics from production ML systems
Daily video processing scale
Real-time inference speed
TensorRT + NVDEC optimization
Crime prevention accuracy
Built & scaled ML team
Infrastructure optimization
Technical Achievements
GPU-Accelerated ML Pipeline
Designed end-to-end video processing pipeline with TensorRT 10.9, NVDEC hardware decoding, and zero-copy GPU operations.
GenAI Synthetic Data Pipeline
Built human-in-the-loop annotation system with GenAI-driven synthetic data generation for training data augmentation.
Real-time Threat Detection
Multi-model ensemble for trespass, theft, and anomaly detection powering nationwide security deployments.
MLOps & Model Versioning
Automated retraining orchestration with reproducible experiments, A/B testing, and gradual rollouts.
Professional Experience
Director, Machine Learning
Cloudastructure Inc
Remote / Bangalore / Salt Lake, India
Machine Learning Engineer
Quantiphi Analytics Solutions Pvt. Ltd. / AthenasOwl
Business Technology Analyst
Deloitte USI Consulting
Technical Expertise
Languages
4 skills
Frameworks, Libraries and Tools
12 skills
Databases
7 skills
Concepts
7 skills
Things I'm Learning
5 skills
Speaking & Talks
Rolling with Python: Intro to Python Wheels
BangPypers Meetup 2024, Bangalore
Introduction to Python Wheels, why it is important, how it helps in packaging and distributing Python libraries. How C/C++ libraries can be included in Python Wheels.
Speeding up Python with Cython
Pycon India 2024, Bangalore / Pycon Japan 2024, Tokyo
Under Core Python: Basic of PVM, Cython, how to speed up Python code, how it helps in Preprocessing and Postprocessing of data with Object Detection.
Education & Certifications
Bachelor of Technology in Computer Science and Engineering
National Institute of Technology, Raipur
2014 - 2018
- Thesis: "Diabetic Retinopathy Detection using Deep Learning"
- Pre-Thesis: Deposist Prediction using Machine Learning Models
- Finalist in the Smart India Hackathon 2018
- Winner of the NIT Raipur Model Making 2017
Data Analyst Nanodegree
Udacity
2018 - 2019
- Completed the Data Analyst Nanodegree
- Projects: Investigate a Dataset, Analyze A/B Test Results, Wrangle and Analyze Data, Communicate Data Findings
- Skills: Python, Pandas, Numpy, Matplotlib, Seaborn, Jupyter Notebook
CS 224w: Machine Learning with Graphs
Stanford Center for Professional Development
2021
- Completed the course on Machine Learning with Graphs
- Skills: Graph Neural Networks, Graph Convolutional Networks, GraphSAGE, Graph Attention Networks
Introduction to High-Performance Computing
CCE Indian Institute of Science, Bangalore
Aug 2023 - Dec 2023
- Single Semester Course on High-Performance Computing
- Skills: MPI, OpenMP, CUDA, Slurm, Parallel Programming
