Yanchuan Sim
Verified Expert in Engineering
Java Developer
Singapore, Singapore
Toptal member since June 6, 2016
Yanchuan is a PhD candidate in language technologies from Carnegie Mellon University with over seven years of experience working with machine learning systems and cutting-edge technologies in natural language processing. Currently, he works with several startups to incorporate ML and NLP technologies into their products.
Portfolio
Experience
- C++ - 15 years
- Java - 15 years
- Python - 11 years
- Machine Learning - 8 years
- Natural Language Processing (NLP) - 7 years
- Generative Pre-trained Transformers (GPT) - 7 years
- Deep Learning - 5 years
- Docker - 3 years
Preferred Environment
Git, Sublime Text, OS X, Linux
The most amazing...
...project I've worked on is a method to uncover and measure the ideological stances of election candidates through their speeches.
Work Experience
Co-founder & CTO
Bot MD
- Co-founded and scaled a healthcare AI company from prototype to production deployments across 27 healthcare organizations in Asia.
- Defined the technical vision and personally architected conversational assistants, enterprise search, workflow automation, and RAG systems for clinicians.
- Built retrieval pipelines combining semantic search, structured knowledge, and enterprise data sources for AI assistants serving 100,000 monthly active users.
- Established company-wide architecture, engineering, and security standards and delivered ISO 27001, ISO 27017, ISO 27018, SOC 2 Type II, and SOC 3 compliance.
Software Engineer
Stravito
- Architected and technically led a multi-agent deep research assistant that combined filtered RAG, LLM-generated SQL, web search, and paid market-intelligence sources.
- Delivered a production research system that reached approximately 7,000 monthly queries, with usage growing 20% month over month for six consecutive months.
- Deployed a shared LLM platform spanning OpenAI, Anthropic, Gemini, and self-hosted models, with centralized routing, rate limiting, failover, observability, and cost attribution.
- Designed a multimodal retrieval platform managing more than 90 million vectors across 100+ enterprise tenants, multiple embedding models, and multiple vector databases.
- Established standards for LLM orchestration, retrieval, and observability, reducing production investigation time by 80% through Langfuse and Claude-powered debugging workflows.
- Led the decomposition of the AI platform into independently deployable services and defined its migration path from Pinecone to AWS-managed vector infrastructure.
Software Engineer
GoodNotes
- Built and operated Kotlin and Go back-end services supporting more than 20 million monthly active users and 250,000 requests per second.
- Owned an Ory Kratos authentication platform handling over 100,000 peak authentication requests per second using a stateless JWT architecture.
- Led a multi-week, zero-downtime migration of more than 10 million Apple iCloud accounts, coordinating rollout, monitoring, and rollback across infrastructure, mobile, and product teams.
- Built back-end infrastructure for customer-facing AI features, including AI Notes and Magic Lasso, while improving reliability, observability, and operational performance.
Research Scientist
Institute for Infocomm Research (A*STAR)
- Led research and development for multilingual NLP systems spanning topic detection, entity linking, sentiment analysis, and information extraction.
- Achieved state-of-the-art benchmark results while setting technical direction and mentoring NLP engineers and graduate researchers.
- Published multiple peer-reviewed papers at top conferences, ACL, EMNLP, and ICLR.
Research Scientist Intern
Google, Inc.
- Researched large-scale entity-recognition and coreference-resolution algorithms designed to improve the structured understanding of web-scale text.
- Proposed and implemented a novel model for joint inference on named entity recognition/tagging and coreference resolution.
- Developed efficient algorithms for performing inference in the high-dimensional combinatorial space using dual decomposition.
- Utilized techniques including dual decomposition, support vector machine (SVM), conditional random fields (CRF), and graphical models.
Education
PhD in Language and Information Technologies
Carnegie Mellon University - Pittsburgh, PA, USA
Bachelor of Science Degree in Computer Science
University of Illinois at Urbana-Champaign - Urbana, IL, USA
Skills
Libraries/APIs
Natural Language Toolkit (NLTK), OpenNLP, Stanford NLP, Scikit-learn, Matplotlib, libsvm, MPI, Sidekiq, X (formerly Twitter) API, SciPy, NumPy, Google API, Facebook API, jQuery
Tools
Amazon Simple Queue Service (SQS), Apache Solr, Terraform, Amazon Elastic Container Service (ECS), Stanford NER, Sublime Text 3, MATLAB, Subversion (SVN), Apache HTTP Server, Amazon Elastic MapReduce (EMR), Sendmail, Notepad++, LaTeX, Sublime Text, Git, Apache UIMA, Docker Compose, Celery, NGINX, ChatGPT, Claude
Languages
C, Java, HTML, BASIC, Python, C++, Bash, Visual Basic, SQL, Scala, Ruby, PHP, CSS, JavaScript, Julia, Kotlin
Frameworks
Apache Spark, Flask, Bootstrap, Django, Spark, Ruby on Rails 4, Ruby on Rails (RoR), Scrapy, Hadoop
Platforms
Linux, Salesforce, Amazon EC2, DigitalOcean, OS X, Amazon Web Services (AWS), Docker, Adobe ColdFusion, Kubernetes
Storage
PostgreSQL, Elasticsearch, Amazon S3 (AWS S3), Redis, Amazon DynamoDB, MySQL, SQLite, MongoDB
Paradigms
Functional Programming, REST, MapReduce
Other
Networks, Deep Learning, Machine Learning, Text Processing, Unsupervised Learning, Sentiment Analysis, Text Mining, Linear Algebra, Convex Optimization, Optimization, Topic Modeling, Neural Networks, Text Classification, Web Scraping, Data Engineering, Data Mining, Data Science, Information Extraction, Natural Language Processing (NLP), Graphical Models, Bayesian Statistics, Statistics, Recurrent Neural Networks (RNNs), Generative Pre-trained Transformers (GPT), Gunicorn, Crowdsourcing, Attribution Modeling, Big Data, Information Retrieval, Search Engines, WebSockets, Chatbots, Amazon Mechanical Turk (MTurk), CrowdFlower, Artificial Intelligence (AI), Probabilistic Graphical Models, Computer Science, LLM Agents, AI Agents, Agentic AI, LLM Reasoning
How to Work with Toptal
Toptal matches you directly with global industry experts from our network in hours—not weeks or months.
Share your needs
Choose your talent
Start your risk-free talent trial
Top talent is in high demand.
Start hiring