On AI Lounge since Oct 2026
James W. Niu
Member #1,269DeveloperL3Enterprise AI Architect, Basis Technologies
Open to Staff+ AI roles. Applied AI/ML, FDE. Multi-agent systems, LLM evals, retrieval, voice AI. LangGraph, MCP, A2A, RAG, MLOps. Measured
How karma works. Everyone starts with 5. You get +1 each time another member upvotes one of your posts or comments (your own upvotes don't count), and lose it if they take the upvote back. Post what you're building, answer questions and help other members to earn more.
Achievements
Plugged In ×3Connected sources: GitHub, Hugging Face, LinkedIn, X, website.How: Connected 3 sources (GitHub, LinkedIn, X or a website) in Settings
Plugged In×3Featured
Shipper ×2Projects on your profile.How: Added 5 projects to their profile
Shipper×2
No posts yet
James W. Niu hasn't posted yet.
Pinned projects
Four Forward Deployed Engineer tasks. An MCP server over stdio with strict validation, an MCP security gateway with role based tool filtering, a streaming PII redaction guardrail, and a token aware rate limiter with model failover on sqlite. Python, 267 tests, no network needed.
asynciofailoverguardrailsjson-rpcllm-gateway
mcp
Agentic RAG and text-to-SQL over an insurer's claims, policy documents and OCR'd scans. Each query runs as the asker's own Postgres login under row-level security, and a verifier traces every figure and citation. 0 leaks in 84 permission runs, 0 of 34 held-out answers wrong. FastAPI, pgvector hybrid search, Tesseract, React, OpenTelemetry, Claude.
agentic-aiai-agentsai-chatbotci-cdevals
fastapi
Ask plain questions about customer feedback. Finds urgent issues, themes to escalate and at-risk accounts, each backed by a verbatim quote. Python, FastAPI, CLI chat.
End-of-turn detection for voice agents. Fine-tuned DistilBERT, int8 on CPU at threshold 0.42, 0.949 PR-AUC on a frozen 53-card human gold set, no false speaks on its 27 wait cards, and 0.913 on 96 held-out real-call turns, speaking over 11 of 47. Three referees, gold, regressions and real calls. 33.1 ms end-to-end p95 at concurrency 8.
ai-agentsconversational-aideep-learningend-of-turn-detectionevals
fastapi
A service that reports how a GitHub repository reviews its own work, with an LLM narrative whose every number is checked back against the computed metrics
code-reviewdeveloper-productivity
dockerengineering-metricsevalsfastify
About
Open to Staff+ AI roles. Applied AI/ML, FDE. Multi-agent systems, LLM evals, retrieval, voice AI. LangGraph, MCP, A2A, RAG, MLOps. Measured before believed.
Experience
Sr. Staff AI Engineer | Multi-Agent Systems | Model/LLM Evaluation, Multimodal | Voice AI, Reinforcement Learning, RAG | LLMOps, MLOps, Python, Fine-Tuning | PyTorch/TensorFlow, Docker/Kubernetes | Columbia MSc | LSE BSc
Sr. Staff AI Engineer · Basis
Principal AI Solutions Architect · Advantage Solutions
AI Solutions Engineer · Leadership Circle
Data & AI Architect · Medlytix LLC
Forward Deployed Engineer (FDE) · GeoAlliance Consultants Pte Ltd
Machine Learning (ML) Engineer · M Capital Group (MCG)
Investment Banking Analyst · Nymex Capital Partners LLC