>> SYSTEM READY
ENGINEERING INTELLIGENCE.
RESEARCHING MULTIMODALITY.
BUILDING AGENTS.

SHUOLIN(LEO) YIN

BASED IN TORONTO, CANADA
EST. 2023
Initialize

EXP.

PROFESSIONAL HISTORY
& RESEARCH

  • Orchestrate large-scale experiments on HPC clusters with SLURM; co-author manuscripts under review at Medical Image Analysis, Nature Communications, and npj Precision Oncology.
  • Pretrain and finetune DINOv3 on 300M medical images using H100 GPUs with PyTorch DDP, achieving 10–20% improvements over SOTA.
  • Lead the MICCAI FLARE 2025 technical committee in designing evaluation metrics; release 3 fine-tuned Qwen3/2.5-VL and MedGemma models.
  • Present a self-supervised pathology foundation model at the NeurIPS 2025 SLCPFM Competition, outperforming SOTA across 5 downstream tasks and 3 cancer types.
  • Publish a medical vision-language models paper in the MICCAI Educational Challenge (top 5), open-sourced as an end-to-end training cookbook (200+ GitHub stars).
  • Collaborate cross-functionally with clinicians, translating medical domain knowledge into ML architectures tracked with Weights & Biases.
PyTorch DDPDINOv3H100 / SLURMQwen3-VLMedGemmaWeights & Biases
  • Built a multi-agent system for outbound sales ops covering discovery, evidence retrieval, outreach generation, and CRM follow-up with LangGraph and MCP.
  • Implemented citation-first RAG over FDA, CE/MDR references, ARTG, and internal documents, returning sourced excerpts for agent review and audit.
  • Distilled a task-specific SLM from Qwen3-32B, cutting inference cost by 7× while matching quality within 2% on automated + human evals (n=1,500).
  • Shipped a CRM automation agent with an MCP layer coordinating workflow across discovery, compliance, and outreach.
  • Supported pilots across 9 countries by shipping enrichment and retrieval features, reducing research time by 70% and lifting sales-team throughput.
  • Built an eval test set and guardrails; tracked retrieval hit and citation coverage, cutting unsupported claims by 30% via logging and error analysis.
LangGraphMCPCitation-first RAGSLM DistillationMLOps
  • Built HumanOS, a closed-loop autonomous agent that perceives, plans, intervenes, verifies, and learns across HealthKit, camera, and behavioral telemetry.
  • Implemented a tiered long-term memory system using Multi-Query RAG with MRR fusion over pgvector (1536-d) to drive persistent personalization.
  • Built conversational agent flows with OpenAI Agents SDK and LangChain; reached an average post-session user satisfaction of 9/10 across 500 beta users.
  • Shipped agent-driven interventions spanning VoIP, iOS FamilyControls, pledge gates, and multimodal verification, reducing average task delay by 40%.
  • Deployed behavioural analytics with TensorFlow.js and Supabase to track engagement metrics, enabling proactive, data-driven intervention.
  • Productionized infra on Supabase: PostgreSQL + pgvector with RLS, Deno edge functions, pg_cron jobs, and JS bridge handlers across native and React.
OpenAI Agents SDKLangChainpgvectorSupabaseTensorFlow.jsiOS / React Native
  • Synthesized medical MLLM literature through systematic review and experimental methodology toward a TPAMI journal submission.
  • Constructed an end-to-end data pipeline for a multimodal evaluation benchmark with automated quality checks, reducing process time by 75%.
  • Developed a PyTorch multimodal evaluation framework assessing VLM accuracy, robustness, and cross-modal consistency, tracked with MLflow.
  • Coordinated interdisciplinary collaboration between medical experts and researchers, designing annotation protocols and improving accuracy by 40%.
  • Automated medical image labelling workflows in Python with NumPy and Pandas, systematically reducing validation effort.
  • Deployed evaluation infrastructure on GCP Compute Engine with Docker, enabling reproducibility across teams.
Medical MLLMsPyTorchMLflowGCP Compute EngineDocker
  • Engineered a two-tower recommendation system in TensorFlow for volunteer matching, improving match acceptance by 85% on historical placements.
  • Built a real-time analytics dashboard with Firebase and TensorFlow.js, deploying engagement prediction models for churn analysis.
  • Developed a full-stack platform with React Native and React.js using a CI/CD pipeline for consistent, robust application builds.
  • Scaled the non-profit to 50+ members, 100+ partner organizations, and 500+ monthly active users through a four-tier management system.
TensorFlowTensorFlow.jsFirebase / FirestoreReact NativeReact.jsCI/CD

PUBS.

PUBLICATIONS
& PRESENTATIONS

01First Author

From Concept to Code: A General Framework for Building a Medical Vision-Language Model

Open-source end-to-end training cookbook for practitioners building medical vision-language models — from data curation to deployment (200+ GitHub stars).

MICCAI Educational Challenge
2025 · Challenge
Top 5
02First Author

Adapting Pathology Foundation Models for Prediction of Homologous Recombination Deficiency Status in High-Grade Serous Carcinomas Using Whole-Slide Images

Adapting pathology foundation models to predict HRD status from whole-slide images of high-grade serous carcinomas.

npj Precision Oncology
2026 · Journal
Under Review
03Co-author

Self-Configuring Multi-Task Learning for Joint 3D Biomedical Image Segmentation and Classification

Medical Image Analysis
2026 · Journal
Under Review
04Second Author

Benchmarking and Adapting On-Device Large Language Models for Clinical Decision Support

Nature Communications
2026 · Journal
Under Review
05Presenter

Pathology-Native Self-Supervision at Scale: DINOv3 for Cancer Foundation Models

Outperformed CONCHv1.5 and UNIv2 across 5 downstream pathology tasks and 3 cancer types.

NeurIPS SLCPFM Competition
2025 · Workshop
Presented
06Organizer

FLARE — Fast, Low-resource, Accurate, Robust, and Effectual Medical Image Analysis Challenge

Technical committee — designed evaluation metrics and released 3 fine-tuned Qwen3/2.5-VL and MedGemma models.

MICCAI
2025 · Challenge
Organizer
6 ITEMS · MEDICAL AI · MULTIMODALITY · FOUNDATION MODELSONGOING RESEARCH

PROJECTS

SELECTED BUILDS

AI AGENTS
FULLSTACK
RESEARCH

01
React NativeYOLOv11RAG / LangChain

Echo – AI-Powered Sustainable Fashion Marketplace

Lead Engineer // Mar 2025

02
OpenAI Agents SDKMCPRAG

EZ-Career – Autonomous AI Job Application Agent

AI & Full Stack Engineer // Apr 2024 – Jun 2024

03
React NativeLangChainAWS Lambda

YiXing – AI-Driven Personalized Travel Planner

Project Lead / Co-Founder // Jun 2023 – May 2024

04
React NativeFastAPIFew-shot Learning

ReassurED – LLM-Powered Emergency Care Navigator

Project Lead // Sep 2024

TECHNOLOGIES

LIVE
PythonJavaC/C++JavaScriptTypeScriptSQLBashRMATLABPyTorchTensorFlowJAXTransformersLangChainOpenCVYOLOscikit-learnRAGReact/React NativeNext.jsNode.jsExpressFastAPIFlaskPostgreSQLNoSQLFirebaseSupabaseRESTful APIsCI/CDGCPCompute EngineTPUFirestoreCloud RunVertex AIAWSEC2S3SageMakerDynamoDBBedrockAzure MLMulti-Agent SystemsOpenAI Agents SDKModel Context Protocol (MCP)Agent OrchestrationDockerKubernetesSLURMMulti-GPU Training (DDP, FSDP)Distributed SystemsWeights & BiasesMLflowPythonJavaC/C++JavaScriptTypeScriptSQLBashRMATLABPyTorchTensorFlowJAXTransformersLangChainOpenCVYOLOscikit-learnRAGReact/React NativeNext.jsNode.jsExpressFastAPIFlaskPostgreSQLNoSQLFirebaseSupabaseRESTful APIsCI/CDGCPCompute EngineTPUFirestoreCloud RunVertex AIAWSEC2S3SageMakerDynamoDBBedrockAzure MLMulti-Agent SystemsOpenAI Agents SDKModel Context Protocol (MCP)Agent OrchestrationDockerKubernetesSLURMMulti-GPU Training (DDP, FSDP)Distributed SystemsWeights & BiasesMLflow
MLflowWeights & BiasesDistributed SystemsMulti-GPU Training (DDP, FSDP)SLURMKubernetesDockerAgent OrchestrationModel Context Protocol (MCP)OpenAI Agents SDKMulti-Agent SystemsAzure MLBedrockDynamoDBSageMakerS3EC2AWSVertex AICloud RunFirestoreTPUCompute EngineGCPCI/CDRESTful APIsSupabaseFirebaseNoSQLPostgreSQLFlaskFastAPIExpressNode.jsNext.jsReact/React NativeRAGscikit-learnYOLOOpenCVLangChainTransformersJAXTensorFlowPyTorchMATLABRBashSQLTypeScriptJavaScriptC/C++JavaPythonPythonJavaC/C++JavaScriptTypeScriptSQLBashRMATLABPyTorchTensorFlowJAXTransformersLangChainOpenCVYOLOscikit-learnRAGReact/React NativeNext.jsNode.jsExpressFastAPIFlaskPostgreSQLNoSQLFirebaseSupabaseRESTful APIsCI/CDGCPCompute EngineTPUFirestoreCloud RunVertex AIAWSEC2S3SageMakerDynamoDBBedrockAzure MLMulti-Agent SystemsOpenAI Agents SDKModel Context Protocol (MCP)Agent OrchestrationDockerKubernetesSLURMMulti-GPU Training (DDP, FSDP)Distributed SystemsWeights & BiasesMLflow