Subash Pandey | Remote AI/ML Engineer (GenAI, RAG, LLMOps)

Subash Pandey | Remote AI/ML Engineer (GenAI, RAG, LLMOps) Subash Pandey Building production-ready AI systems for real business outcomes. Remote AI/ML engineer focused on GenAI products, RAG systems, and LLM reliability. Projects Gavel GenAI / Multi-Agent Workspace for shaping startup ideas, collecting evidence, and running structured multi-agent judgment. Five parallel judges, LangGraph debate, readiness gates, versioned worksheets, post-run handoffs, and a FastAPI SSE run engine with a durable SQLite event log. LangGraph Python FastAPI Next.js SQLite Cloud Native AI Platform MLOps / Platform Cost-bounded cloud-native AI summarization platform: FastAPI + Kubernetes/Helm, Terraform on Hetzner, GitOps via Argo CD, full observability stack. Next up: autoscaling, canary deploys, DR. Runs under $15/month. Kubernetes Helm Terraform FastAPI Argo CD Prometheus Grafana Loki Gitops Hetzner Activity Recognition ML / Sensors Classified human physical activities (walking, jogging, sitting, typing, etc.) using XGBoost on accelerometer and gyroscope data from smartphones and watches. Hyperparameter tuning via random search achieved >85% accuracy. XGBoost Python scikit-learn Feature Engineering Steam Video Game ML Network Analysis Explored the evolution of game genres on Steam using network analysis. Identified emergent sub-genres, influential genre nodes, and key drivers of player engagement including ratings, achievements, and pricing models. Wikipedia Adminship Network Analysis Investigated social network dynamics within Wikipedia's administrator election process. Calculated centrality measures, performed community detection via hierarchical clustering, and analyzed voting blocs. NetworkX Python Community Detection Clustering Floki eCommerce Full-Stack Full-stack e-commerce application built with the MERN stack. Features include product browsing, searching, filtering, cart management, user authentication, order processing, and