Niteesh
Kanungo
Architecting robust high-throughput distributed systems, clinical genomics pipelines, and multi-agent AI ecosystems.
Specialized Expertise
Bridging the gap between raw datasets and intelligence layers through robust engineering and resilient distributed systems.
Data Engineering & Pipelines
Architecting high-throughput distributed systems capable of processing 10TB+ daily telemetry with 99.99% operational uptime.
AI & Machine Learning
Deploying production-grade CNN and NLP models on AWS SageMaker for automated clinical diagnostic verification and real-time image auto-moderation.
Cloud Infrastructure
Designing resilient AWS and Azure ecosystems using Terraform, multi-region Kubernetes orchestrations, and serverless server pipelines.
Full-Stack Development
Building blazing-fast web applications with Next.js, React, Node.js, and modern CSS for micro-telemetry and real-time data visualisations.
IoT & Edge Computing
Integrating edge gateway hardware (Raspberry Pi/NVIDIA Jetson) with industrial GPS tracking modules and high-frequency accelerometers.
Big Data Analytics
Extracting clinical and transactional insights from petabyte-scale distributed data lakes using PySpark, Databricks, and Presto query federations.
Featured Showcase
A deep dive into high-impact engineering architectures and automated data ecosystems.
AUTOMATED DEEP LEARNING AT SCALE
AI-Driven Content Moderation
Architected a computer vision model pipeline for Bazaarvoice that automated the verification of millions of consumer images. Saved over $100k annually by replacing manual workflows and achieving 82%+ categorization accuracy using AWS SageMaker pipelines.
INDUSTRIAL TELEMETRY & TRACKING
Real-time IoT Intelligence
Built a hardware-to-cloud telemetry tracking system for heavy assets. Integrated industrial GPS sensors and Edge Gateway logs (Raspberry Pi/NVIDIA) to feed low-latency geo-fencing diagnostics to AWS Data Lakes.
Insights & Discovery
Beyond the enterprise—exploring paradigms through photography, writing, and local AI sandboxes.
Blog
Reflections on engineering paradigms, design philosophy, and ideas at the nexus of technology and culture.
Photography
Visual diaries captured through prime glass. Capturing lighting, high-contrast architectures, and structural silence.
The Lab
Home infrastructure projects, local AI gateway testing, GPU clusters, and experimental cyber-physical scripts.
Professional Experience
A decade of architecting clinical genomics and IoT data infrastructure.
Lead Platform Engineer
- Architecting multi-cloud genomic and clinical data platforms for precision oncology medicine.
- Optimizing massive ETL pipelines scaling to petabytes of healthcare records and sequencing readouts.
- Collaborating with clinical AI research units to deploy deep learning models seamlessly into live diagnostic streams.
Senior Data Engineer
- Built foundational data lake architecture on AWS and GCP processing 10TB/day of clinical and sequencing data.
- Pioneered PHI de-identification pipelines using AWS Batch and GKE, enabling compliant downstream analytics.
- Productionized Airflow + DBT workflows powering biomarker discovery and clinical reporting dashboards.
Data Engineer II
- Consolidated 44 siloed fleet GPS telemetry tracking engines into a single unified high-efficiency pipeline.
- Processed over 10TB+ daily industrial logs for global predictive logistics and preventative mechanical maintenance.
- Significantly improved pipeline data availability through automated self-healing and alert configurations.
Data Scientist
- Developed CNN models using AWS SageMaker for automatic moderation of user review media (82%+ classification accuracy).
- Saved $92k-$100k annually by replacing manual manual verification queues with automated deep learning workflows.
- Developed insight extraction and named-entity sentiment scripts using Python NLTK and Flask APIs.
Data Analyst
- Analyzed operational power turbine logs for the Abbott facility using SQL and Python regression trees.
- Delivered data-driven dashboards reducing downtime by 12% through targeted preventative maintenance strategies.
- Presented monthly analytical telemetry audits to facility engineering leadership.
Education
Academic credentials in Computational Systems and Data Science.
UIUC
Masters (M.S.) – Information Management/Data Science
Dec 2018
JNU Delhi
Graduate Research Fellow – Structural Biology
2014
Featured Work
A curation of laboratory repositories and enterprise solutions.
Automated Rating System
Developed a distributed system using Python and PostgreSQL for real-time rating aggregation, scaling, and heavy telemetry analysis.
Research & Publications
Academic journal contributions at the interface of biotechnology and database systems.
Digital Footprint
Connecting the dots across the scientific and professional web networks.