.png){kind=logo}
Junhui Huang
Intern Machine Learning Engineer specializing in LLMs, MLOps, and NLP
Connect with Junhui
Junhui already has a relationship with Reval, so a warm intro from us gets a much better response than cold outreach.
Recommended
Already have an account?
About
Built and deployed a production LLM-driven Dungeons & Dragons game where the model acts as a dungeon master, adding a structured combat system and a macro-state tree to ensure campaigns converge to a clear ending. Fine-tuned Gemini 2.5 Flash on Vertex AI and deployed on GCP with Kubernetes, using RAG over DnD rules/spells plus multi-agent orchestration (intent-based routing between narrative and combat agents) to reduce hallucinations and improve reliability.
Experience
Education
Key Strengths
- Built and deployed an LLM-powered Dungeons & Dragons game to production
- Reduced hallucinations using RAG with DnD rules/spells injected into prompts
- Designed a macro-state tree framework with guardrails and allowed transitions to control narrative
- Implemented multi-agent routing (narrative vs combat) using intent classification
- Pragmatic orchestration tradeoffs: hard-coded routing for reliability vs LangGraph for scalability
- Reliability-focused testing approach (unit + system/simulation tests)
- Performance-driven evaluation using latency, token usage, hops per task, and failure rate
Discover more candidates like Junhui
Search across thousands of pre-screened, high-quality, high-intent candidates on Reval.
Search Talent