Varun Chauhan

Hi, I’m currently pursuing a Master’s degree in Computer Science at the University of California, Irvine.

I have extensive working knowledge as a Software Engineer with a very good understanding of agile methodologies, cloud technologies and software development lifecycle. In the past couple of years, I have worked on some very interesting problems like memory leakages, container memory management, message broking, asynchronous schedulers, network latency, caching strategies, and security vulnerabilities. Apart from these, my regular work day involves architecting microservices, API design and development, performance testing, and pipelining.

My previous research experience includes ML-powered Lab-on-Chip cytometry, a bit of distributed ML, geospatial image processing, and a bit of smart contracts in Solidity.

Experience

Cloud Reliability Engineer Intern

Viant

(June, 2024-Present)

Developed metrics collection service using OpenTelemetry, FastAPI, and Logz.io.
Scripted GitHub workflows for automating testing, containerization, and deployments to AWS EKS.
Worked extensively with Helm charts and ArgoCD for managing EKS deployments.

Software Engineer

Soroco

(November, 2020-August, 2023)

Assumed end-to-end ownership of Python, Java and Go based microservices and developed REST APIs in Django and Flask frameworks with PostgreSQL backend.
Revamped the authorization and authentication framework in the existing software by creating wrappers to support the new flow in Python and Go.
Worked with Kubernetes for horizontally scaling Podman and Docker containerized services.
Led the team’s security initiatives using platforms such as Veracode and Snyk for detecting and fixing security vulnerabilities in python code resulting in an 82% improvement in security metrics.
Improved authorization response time by 60% by designing and implementing an efficient Redis cache for user authorization information which supported constant time O(1) lookup for 95% of the cases.
Leveraged observability tools such as Datadog and Elastic to monitor performance and discover bottlenecks.

Data Scientist Intern

Wipro

(January-May, 2020)

Worked with one of the largest telecom providers in the world to create a product to proactively monitor SNMP event logs using event correlation, clustering, and predictive analysis.
Created 172 situations from 3859 alarms with 87% accuracy based on the correlation of the alarms, and performed root cause analysis.
Incorporated functionalities such as dynamic update of the element correlation and resolution suggestion.

Machine Learning Engineer Intern

Oil and Natural Gas Corporation

(June-July, 2019)

Developed U-Net with skip connections for the generative model and generated seismic survey paths with an accuracy of 72%.
Processed images in parallel using Apache Spark to achieve speedup by a factor of 8.

Education

Sep, 2023	University of California, Irvine Master of Computer Science GPA: 4.0/4.0 Coursework: Parallel and Distributed Computing, Data structures, Machine Learning, Artificial Intelligence, Machine Learning, Probabilistic ML with generative models Graduation: December, 2024

Projects

ML-powered DIH image cytometry

Dr. Mohendra Roy, PDPU, Gandhinagar; Dr. Sungkyu Seo, Korea University, Seoul

Image Processing of DIH images for cell-characterization.

Low-cost ELISA microplate reader

Dr. Abhijit Roy, IISc, Bangalore; Dr. Mohendra Roy, PDPU, Gandhinagar

Enzyme-linked immunosorbent assay reader powered by neural network-based segmentation and spectroscopy.

Distributed Image Processing

Varun Chauhan

Implemented a distributed version of Image processing algorithms using U-Net to classify landforms from satellite images.

Publications

Biosensors

Machine Learning Based Lens-Free Shadow Imaging Technique for Field-Portable Cytometry

Biosensors, Feb 2022

Abs VIEW

The lens-free shadow imaging technique (LSIT) is a well-established technique for the characterization of microparticles and biological cells. Due to its simplicity and cost-effectiveness, various low-cost solutions have been developed, such as automatic analysis of complete blood count (CBC), cell viability, 2D cell morphology, 3D cell tomography, etc. The developed auto characterization algorithm so far for this custom-developed LSIT cytometer was based on the handcrafted features of the cell diffraction patterns from the LSIT cytometer, that were determined from our empirical findings on thousands of samples of individual cell types, which limit the system in terms of induction of a new cell type for auto classification or characterization. Further, its performance suffers from poor image (cell diffraction pattern) signatures due to their small signal or background noise. In this work, we address these issues by leveraging the artificial intelligence-powered auto signal enhancing scheme such as denoising autoencoder and adaptive cell characterization technique based on the transfer of learning in deep neural networks. The performance of our proposed method shows an increase in accuracy >98% along with the signal enhancement of >5 dB for most of the cell types, such as red blood cell (RBC) and white blood cell (WBC). Furthermore, the model is adaptive to learn new type of samples within a few learning iterations and able to successfully classify the newly introduced sample along with the existing other sample types.
IEEE ICHI

ANNSESDIHM: An Artificial Neural Network based Signal Enhancement Scheme for Digital Inline Holography (DIH) Microscope

IEEE International Conference on Healthcare Informatics, Feb 2020

Abs VIEW

Digital inline holography (DIH) is a proven technique for cell and microparticle analysis. This technique has been used for auto characterization of microparticles. Recently, it has been used for the characterization of complete blood count (CBC) from a whole blood sample, where the comparable results between the traditional LH750 Haematology analyser and the DIH microscope system show a correlation of 0.87 for red blood cells (RBC) and 0.92 for white blood cells (WBC). However, we observed that the DIH microscope system is very sensitive to dust and other foreign microparticles from the surrounding environment. This hampers the quality of the micrograph. Moreover, the non-uniform illumination also hinders the signal quality of the images of the cell diffraction patterns. To overcome these problems, we have investigated various neural network-based signal enhancement schemes. The results show a significant improvement in the signal quality to that of the noisy version. The study shows that convolutional neural network (CNN) architecture is performing better in terms of signal improvement compared to the extreme learning machine (ELM). However, the ELM network is converging faster (within 1 epoch) compared to CNN. Also, we have studied the same with a fully connected network, which shows no improvement in the signal quality even for noises with low variance. The result demonstrates that we can use the unsupervised method, such as autoencoder (CNN) to improve the signal quality.