Unclaimed profileBuilt from public GitHub and Hugging Face activity. Debu has not joined Lounge yet.Claim it
Not on Lounge yet
Debu Sinha
developerLead AI/ML Solutions Architect @ Databricks | GenAI eval infra: MLflow, Inspect AI, SycoBench, Semantic Illusion | Packt author/reviewer
Public projects
agentsec
Security scanner and hardener for agentic AI installations - OpenClaw, MCP servers, and AI agent skill ecosystems
Python
mlflow-eval-workshop
Workshop: Evaluating LLM Applications with MLflow - ODSC AI West 2026
Python
sycobench-600
ACL Findings benchmark for measuring LLM sycophancy and correction selectivity
Pythonaclacl-2026ai-safety
excalidraw-mcp-server
Security-hardened MCP server for Excalidraw with API key auth, rate limiting, real-time WebSocket sync, and 14 diagramming tools
TypeScript
omnigent-mlflow-quickstart
MLflow tracing adapter for omnigent agents. One span per StreamHooks callback, one trace per turn.
Pythonagentsai-agentsdatabricks
techfutures-2025-mlops-databricks
End-to-end MLOps workshop on Databricks — learn how to train, track, register, and deploy ML models using PyTorch, MLflow, and Unity Catalog, with extensions to LLMOps via Mosaic AI.
Python
Likely stack
PyTorchMCPReact
