10 projects
Driver Behavior Analytics
Dec 2024 · Bayesian Analytics

Driver Behavior Analytics System

Driver risk analytics for 300K+ drivers using survival analysis & Bayesian modeling, with real-time assessment APIs.

88% accuracy 10K+ daily req <200ms
KafkaPyMC3FastAPIPostgreSQL
View case study
LLM Serving Framework
May 2025 · LLM Infrastructure

Production LLM Serving Optimization

vLLM continuous batching, INT8/INT4 quantization and multi-GPU tensor parallelism for enterprise-scale inference.

12.3K req/s 42ms P50 70% memory cut
vLLMFastAPIK8sPrometheus
View case study
Search Relevance Ranking
Dec 2024 · Information Retrieval

Search Relevance & Ranking System

Production search engine with LambdaMART ranking across 500K+ queries, plus a comprehensive A/B testing framework.

nDCG@10 0.847 +18.3% CTR <200ms P95
XGBoostscikit-learnFlaskBM25
View case study
AgentForge Multi-Agent RAG
Nov 2024 · Multi-Agent RAG

AgentForge Multi-Agentic AI RAG

Multi-agent RAG with LangGraph orchestration for autonomous research, document generation and intelligent retrieval.

98.5% success −67% cost 180ms P95
LangChainLangGraphGPT-4Redis
View case study
Face Mask Detection
Nov 2023 · Computer Vision

Face Mask Detection

Real-time face mask detection using deep CNN with transfer learning for automated safety compliance.

99.6% accuracy <50ms inference 500+ concurrent
TensorFlowVGG16Flask
View case study