Developed a microservices-based tech blog platform focused on AI, cybersecurity, GCP and Linux, averaging 120+ monthly visitors. Hosted on Google Cloud Run (99.95% uptime SLA) and backed by Cloud Storage (99.95% availability SLA) for low-latency, high-availability static asset delivery. Leveraged Cloud CDN to cache content at Google Cloud’s global edge locations, reducing load times for users across regions, and integrated Text-to-Speech to enhance accessibility for visually impaired users. Automated log ingestion pipelines with BigQuery as the centralized data sink for real-time analytics, supported by Cloud Logging for continuous observability. Implemented CI/CD using GitHub to ensure seamless, version-controlled deployments.

Created a Graph Retrieval-Augmented Generation (GraphRAG) web app that answers Mission: Impossible questions with context-aware, generative responses. The system enhances traditional RAG by combining cosine-similarity search on semantic embeddings with a dynamically constructed knowledge graph, enabling deeper contextual understanding. A Flask backend builds and queries the graph using NetworkX, while a language model generates responses based on rich subgraph context. The application runs under Gunicorn (WSGI) and is fronted by NGINX as a reverse proxy, with communication handled via a Unix socket for secure, low-latency performance. Hosted on multi-zone Google Compute Engine, the service leverages GCE’s 99.99% uptime SLA, with tightly scoped ingress rules for high-performance, secure access.

Fine-tuned the Gemma 2B language model using LoRA (Low Rank Adaptation) on 4,000 samples from the Stanford Alpaca dataset. Utilized TensorFlow, KerasNLP, and JAX to train on an A100 GPU, significantly reducing trainable parameters from 2.6 billion to 2.9 million for efficient optimization. The fine-tuned model exhibited lower perplexity, higher accuracy, and improved instruction-following capabilities across a range of domains.

Designed and deployed a secure, real-time log-analytics platform on Google Cloud that ingests, processes, and visualizes network logs end to end. Architected a custom Virtual Private Cloud (VPC) sliced into three /24 subnets—x.y.1.0/24 (web), x.y.2.0/24 (application), and x.y.3.0/24 (processor)—each pinned to dedicated Compute Engine VMs to enforce zero-trust micro-segmentation and east-west isolation. Granular, stateful firewall rules admit traffic only from whitelisted IP prefixes and service accounts. Logs are encrypted in flight over SSH, transformed with Python, staged in Cloud Storage, and streamed through Pub/Sub to invoke Cloud Functions (1st gen.) that load structured data into BigQuery. A hardened Flask API—exposed via HTTPS and IAM-based authentication—delivers controlled, low-latency access to analytics, providing scalable, compliant, and high-performance troubleshooting insights.

Built an interactive visual learning platform (Graphil) using React to simplify complex technical topics—including Linux, GCP, networking, Python, and AI—through modular, pre-rendered visualizations. The intuitive UI/UX design enables self-guided exploration of technical subjects, enhancing comprehension for visual learners. The platform is open-source, encouraging community collaboration and extensibility.

Compiled a comprehensive and holistic compliance framework covering 15+ critical domains (e.g., Cybersecurity/CyberSecOps, Data Privacy (GDPR, CCPA), PCI DSS, IT Best Practices, Legal & Operational Standards) for a fictional grocery delivery startup. This proactive resource demonstrates the potential to streamline onboarding and reduce initial legal/compliance research overhead by an estimated 5–10%.