Projects

Shipping AI/ML applications. Each project links to its GitHub repository.

RAG Document Q&A Completed
GitHub →

Upload any PDF or text document and ask questions conversationally. Built on Amazon Bedrock (Titan Embed v2 + Claude 3.5 Haiku), ChromaDB for vector storage, and FastAPI. Streaming responses with inline [Source N] citations and multi-turn conversation memory per session.

RAG LangChain AWS Bedrock ChromaDB FastAPI
DocAssistant — Production RAG In Progress
Coming Soon

Enterprise-grade "Ask Our Docs" system with hybrid retrieval (BM25 + vector search), cross-encoder reranking, citation enforcement, and CI-gated evaluation pipeline. Production-ready with Ragas metrics (faithfulness, answer relevance, context precision) integrated into GitHub Actions.

Hybrid Retrieval Cross-Encoder Ragas Evals CI/CD LangChain
PrivacyLLM — Local SLM Benchmarks Pending
Coming Soon

Privacy-first tool to run, benchmark, and compare local models entirely offline. Compare 3 quantized models (Mistral 7B, Llama 2, Phi) on quality (accuracy/BLEU) vs. latency (p50/p95) vs. memory usage. FastAPI wrapper with streaming support and interactive dashboard.

Ollama Local Models Benchmarking FastAPI
JSON Extraction Specialist — Fine-Tuning Pending
Coming Soon

Fine-tune Llama 2 7B with LoRA + DPO to extract structured data from unstructured text (contracts/invoices). Phase 1: SFT on extraction task. Phase 2: DPO to prefer correct JSON format. Baselines against GPT-3.5 with before/after metrics (exact match %, F1 score, latency).

LoRA DPO Llama 2 Fine-tuning
AWS Security GitHub →

Deep-dive into AWS security services and patterns — IAM least-privilege design, Security Hub findings, GuardDuty threat detection, and KMS encryption strategies. Practical reference for securing cloud workloads at the architecture level.

Security AWS IAM GuardDuty Security Hub
RAG Document Q&A — Security Applications GitHub →

The RAG pipeline applied to security documentation — query threat reports, CVE databases, and compliance frameworks conversationally. Forms the foundation for agentic STRIDE and ATLAS threat modeling workflows using Claude.

STRIDE ATLAS LLM Threat Modeling
OrderStream — Secure Microservices GitHub →

Python microservices platform demonstrating secure-by-design patterns: IAM-controlled SQS/Kinesis access, encrypted PostgreSQL connections, API Gateway authorization, and secrets management via AWS Secrets Manager.

Security AWS Python Microservices
Algorithms & Data Structures GitHub →

Practice implementations across sorting, searching, graphs, trees, and dynamic programming — collected from LeetCode, HackerRank, GeeksForGeeks, and Codility. Written in Java with complexity annotations on each solution.

Algorithms Java Big-O
Dynamic Programming GitHub →

Focused collection of dynamic programming solutions — knapsack, LCS, edit distance, coin change, matrix chain multiplication, and more. Each solution includes the recurrence relation, memoization and tabulation variants, and complexity analysis.

Dynamic Programming Java
LeetCode Solutions GitHub →

LeetCode problem solutions organized by pattern: sliding window, two pointers, binary search, BFS/DFS, backtracking, and union-find. Consistent structure makes it easy to recognize patterns in new problems.

Algorithms Java LeetCode
Codility Solutions GitHub →

Efficient solutions to Codility algorithm challenges with a focus on time and space complexity. Covers prefix sums, caterpillar method, leader algorithms, and prime/composite sieve patterns.

Algorithms Java Codility
HackerRank Solutions GitHub →

317+ solutions to HackerRank algorithm and data structure challenges. Covers arrays, strings, trees, graphs, greedy algorithms, and SQL. Organized by domain and difficulty.

Algorithms Java SQL
OrderStream — Microservices Platform Completed
GitHub →

Python microservices platform built on AWS SQS, Kinesis, API Gateway, and PostgreSQL. Models a real e-commerce order processing domain — order intake, fulfillment, inventory, and notifications — as independent services communicating via events.

SQS Kinesis API Gateway Python PostgreSQL
RAG Document Q&A — Bedrock Pipeline Completed
GitHub →

End-to-end AI pipeline on AWS Bedrock — Titan Embed v2 for vector embeddings, Claude 3.5 Haiku for generation, ChromaDB for local vector storage. Includes a CDK deployment stack for ECS Fargate + EFS + ALB.

AWS Bedrock CDK ECS Fargate RAG
RAG Observability Platform Pending
Coming Soon

Production monitoring for RAG systems. Track latency (p50/p95/p99), cost-per-request, quality metrics (Ragas), and token efficiency. CI regression gating: fail if quality drops >5% or latency > 2s. Dashboards in Langfuse + Grafana with custom eval framework.

CloudWatch Langfuse Observability CI/CD
VoiceAssistant — Real-Time Multimodal Pending
Coming Soon

Voice-enabled chatbot (speak → transcribe → respond → speak) with <1s end-to-end latency. Deepgram for ASR, Claude API for generation, ElevenLabs for TTS. Latency budget breakdown, graceful degradation, and timeout handling. Built with Pipecat framework and FastAPI.

AWS Deepgram Real-time WebSocket