.png){kind=logo}
Mengyu Liu
Senior Data Scientist specializing in GenAI agents and causal inference
Connect with Mengyu
Mengyu 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 healthcare medical review agent that automates call-transcript summarization and medication reconciliation using a hybrid deterministic + LangGraph-orchestrated LLM workflow. Demonstrates strong reliability engineering (guardrails, schema validation, confidence thresholds, golden/adversarial eval, Langfuse monitoring) in a regulated environment, delivering 60% lower latency and 70%+ efficiency gains while partnering closely with care managers and operations.
Experience
Education
Key Strengths
- Built and deployed a production medical review agent for summarization + medication reconciliation from long healthcare call transcripts
- Hybrid deterministic + LLM design to reduce hallucinations in a regulated setting (NER/regex/rules + LLM synthesis)
- Designed guardrails: schema validation, domain constraints, confidence thresholds, and human-review fallbacks
- Strong evaluation discipline: custom field-level metrics, golden dataset regression suite, and adversarial edge-case testing
- Operationalized LLM systems with tracing/monitoring (Langfuse) and audit sampling in production
- Workflow orchestration expertise: stateful LangGraph graphs with branching/retries to reduce latency and cost
- Delivered measurable production impact: 60% latency reduction and 70%+ processing efficiency improvement
- Effective collaboration with non-technical healthcare stakeholders (care managers/ops) to define requirements and drive adoption
Discover more candidates like Mengyu
Search across thousands of pre-screened, high-quality, high-intent candidates on Reval.
Search Talent