Sameer Saxena

Engineer & Data Enthusiast | Turning Data into Decisions, Automation into Impact

Currently pursuing a Master of Science in Data Science at Northeastern University, my journey in technology began with a Computer Science degree from Manipal Institute of Technology. My experience spans from working as an undergraduate research assistant and publishing papers to interning as a Data Engineer and later contributing to Shell's Cyber Defence team. Over time, I've built expertise in Machine Learning, Computer Vision, Data Pipelining, and Security, applying these skills across both academic and industry projects.

I enjoy exploring new ideas, whether through research in computer vision or by competing in cybersecurity tournaments like Boss of the SOC. For me, the most exciting part of technology is the constant opportunity to learn, collaborate, and create solutions that make a difference. As I advance my graduate studies, I'm focused on deepening my expertise in data science while continuing to bridge the gap between research and real-world applications.

Get In Touch View Projects
Sameer Saxena

Professional Journey

August 2023 - August 2025
Systems Engineer
Shell
  • Developed license renewal automation system for 200+ applications, saving 100 minutes per renewal per application.
  • Built Splunk dashboards, alerts, and a custom RBAC app to secure vulnerability data and improve monitoring efficiency.
  • Resolved ingestion issues across 5+ critical security log sources including Azure AD, ensuring data reliability.
  • Redesigned ServiceNow workflows with intelligent SLA tracking, reducing incident backlog by 30%.
  • Automated CrowdStrike reporting with Python and Azure DevOps, streamlining access for 10+ teams.
  • Initiated Splunk journey through Boss of the SOC tournament, achieving 7th place among India-Netherlands teams.
January 2023 - July 2023
Data Engineering Intern
BackPac Technologies
  • Developed Looker Studio dashboard for 1,000+ employees across 12+ departments.
  • Performed statistical significance testing (p-value) to check the significance of the data.
  • Executed data cleaning and preprocessing pipelines using Airflow.
  • Created detailed documentation for seamless team onboarding
August 2021 - December 2022
Undergraduate Research Assistant
Manipal Institute of Technology
  • Worked with Dr. Nisha P. Shetty and co-authors on research in dynamic Twitter friend grouping, published in IET Communications
  • Implemented clustering techniques including KMeans, BIRCH, DBSCAN, Spectral, Fuzzy C-Means, Rep-C, and Gaussian Mixture Models
  • Validated clusters using Silhouette Score, Davies-Bouldin Index, Calinski-Harabasz Index, and by calculating Cohesion and Separation
  • Built the model with synthetic data and verified results on real-world datasets such as Ciao and FilmTrust
  • Read the full paper here
January 2020 - June 2022
Core Team Member
Cryptonite - CTF Team
  • Core team member of the Forensics subsystem, specializing in memory forensics
  • Participated in multiple international CTF tournaments as part of Cryptonite
  • Key contributor during the team's first-ever hosted CTF tournament, NITE CTF 2021
  • Team currently ranks in the top 100 globally on CTFtime.org

Technical Skills

Languages

Python SQL C++ JavaScript TypeScript Bash

Data & Machine Learning

Power BI Looker Studio TensorFlow PyTorch Point Cloud Library Image Processing Airflow PySpark Hypothesis Testing

Security & DevOps

Splunk Cloud Splunk SOAR ServiceNow SIR ServiceNow VR ServiceNow Flow Designer Azure DevOps Power Platform

Research & Projects

Published Research

Dynamic Twitter Friend Grouping Using Clustering Techniques

Research on social network analysis and user clustering algorithms published in IET Communications

Read Publication
Machine Learning Clustering Python Scikit-learn
NeurIPS 2021

XCI-Sketch

Generative sketching system using conditional GANs for image-to-sketch translation with perceptual user study

View on GitHub
GANs Computer Vision OpenCV PyTorch Streamlit
AI for Social Impact

Kissan Mitra (Farmer's Friend)

Voice-enabled AI agricultural advisory system supporting 5 Indian languages with real-time weather and pricing data

View on GitHub
AWS Lambda OpenAI Voice API Knowledge Graphs DynamoDB NLP
MakeHarvard 2021

CRSAS - Customer Review Sentiment Analysis System

Sentiment analysis platform with Streamlit dashboard for visualizing customer review insights

View on GitHub
NLP Sentiment Analysis Python Streamlit
FinTech

LendScape

Peer-to-peer lending platform with credit risk assessment and loan recommendation system

View on GitHub
Machine Learning Python Flask Scikit-learn
Graph Analytics

Course Graph Explorer

Interactive visualization tool for exploring course dependencies and academic pathways using graph algorithms

View on GitHub
Graph Analytics Python NetworkX Visualization

Achievements & Recognition

7th Place - Boss of the SOC

Ranked 7th in Shell's cybersecurity tournament among teams from India and Netherlands

2nd Place - Code Innovation Series

Runner-up among 30+ teams in hackathon by Dept. of ICT & GitHub India

Top 3 - MakeHarvard 2021

Nominated for Maker's Choice Award at prestigious Harvard hackathon

2 Research Publications

Published in IET Communications Journal and NeurIPS Workshops

Top 100 CTF Team

Team Cryptonite ranked globally on ctftime.org

Academic Excellence

CGPA 8.99/10 with Minor in Big Data

Let's Connect

I'm always interested in collaborating on projects related to machine learning, data, cybersecurity, and automation. Feel free to reach out!

Email LinkedIn GitHub