# Hao Yang

Hao Yang is a remote worker on Himalayas, AI Service Engineer Intern at Taiwan Semiconductor Manufacturing Company, based in United States.

Source: https://himalayas.app/@haoyang1

```text
I build production AI inference, MLOps, and quantitative trading systems.
```

| Detail | Value |
| --- | --- |
| Availability | Looking for a job |
| Location | United States |
| Authorized to work in | United States |
| Salary expectations | 120k+ USD |
| Job categories | Machine Learning Engineer, Quantitative Developer, MLOps Engineer, AI ML Services Engineer, Software Engineer |
| Skills | Python, JavaScript, TypeScript, C, C++, PyTorch, fastAPI, Django, React, Hugging Face Transformers, MongoDB, PostgreSQL, Redis, S3, Docker, Kubernetes, VLLM, NVIDIA Dynamo, Run:Ai, MLFlow, ArgoWorkflows, AWS, Git, LLM Inference, MLOps, Quantitative Trading, ETL, Data Warehouse, OpenAI Compatible Endpoints |
| Portfolio | https://github.com/yanghao13111 |
| LinkedIn | https://linkedin.com/in/hao-michael-yang |
| GitHub | https://github.com/yanghao13111 |

## What I'm looking for

```text
I'm looking to build production AI, MLOps, or quantitative systems where I can own work from data and infrastructure through reliable, measurable deployment.
```

## About

```text
I deployed five Qwen3-family LLM inference services at TSMC on Kubernetes, using NVIDIA Run:ai, NVIDIA Dynamo, and vLLM to expose OpenAI-compatible APIs for validation and benchmarking.

I configured disaggregated prefill/decode serving and benchmarked inference topologies under 17.6K-token, 32-concurrency workloads. KV-aware routing improved throughput by 46.4% and reduced average time to first token by 49.2%.

At Medina Partners, I brought research trading algorithms into production on AWS, from market-data ingestion through live order execution. I also built a three-tier data warehouse, automated daily ETL for roughly 2,000 securities, and delivered a React and Django portfolio dashboard with live strategy P&L visibility.

In my projects, I shipped an MLOps music recommendation system with 0.80 production AUC and 13ms p95 serving latency, and built an adaptive INT8 KV cache that reduced Mistral-7B memory use by 58.5%.
```

## Experience

### AI Service Engineer Intern

[Taiwan Semiconductor Manufacturing Company](https://himalayas.app/companies/taiwan-semiconductor-manufacturing). Jul 2026 - Aug 2026

```text
Deployed five Qwen3-family PoC LLM inference services on Kubernetes using NVIDIA Run:ai, NVIDIA Dynamo, and vLLM, exposing OpenAI-compatible API endpoints for internal validation and benchmarking. Configured and deployed disaggregated prefill/decode serving on Dynamo, tuning per-role GPU allocation and replica counts, and configuring TCP-based KV-cache transfer between stages.
```

Skills: Kubernetes, Run:Ai, NVIDIA-Dynamo, VLLM, Qwen-3, LLM-Inference, Disaggregated-Serving, KV-Caching, AIPerf, Benchmarking

### Quantitative Developer

Medina Partners. Mar 2024 - May 2025

```text
Developed and deployed trading systems on AWS, engineering the research team's trading algorithms into production, from data ingestion to live order execution. Designed a three-tier data warehouse with an automated daily ETL pipeline ingesting market data across ~2,000 listed securities, and built a full-stack internal portfolio dashboard with React and Django.
```

Skills: AWS, Data-Engineering, ETL, Data-Warehouse, Trading-Systems, Order-Execution, Broker-API-Integration, React, Django, Fullstack-Development, Python

## Education

### New York University

Master of Science, Computer Engineering. 2025 - Present

```text
Pursuing a Master of Science in Computer Engineering at New York University, with an expected graduation in January 2027.
```

### National Taiwan University

Bachelor of Science, Biomedical Engineering. 2020 - 2024

```text
Earned a Bachelor of Science in Biomedical Engineering with a minor in Computer Science and Information Engineering from National Taiwan University.
```

## Tech stack

- Kubernetes
- PostgreSQL
- MongoDB
- Django
- Redis
- React
- JavaScript
- Python
- C++
- C
- PyTorch
- MLflow
- FastAPI
- TypeScript
- Git
- Docker
- vLLM
- Run:AI

To contact Hao, message them from this profile with a Himalayas employer account: [Hire on Himalayas](https://himalayas.app/hire).

## People also viewed

- [Tianchang Liu](https://himalayas.app/@ismaeltc): Senior AIOps Manager, Tredence
- [Davante Bonham](https://himalayas.app/@davantebonham): Senior Python | Machine Learning Engineer, Fingent
- [Ahmed Abid](https://himalayas.app/@ahmedabid): Staff Machine Learning Engineer, ServiceNow
- [Ryan Smith](https://himalayas.app/@ryansmith4): Senior Machine Learning Engineer, PivotKing LLC
- [Wei Yang](https://himalayas.app/@weiyang): AI/ML Engineer, Intuitive
- [Jack Wang](https://himalayas.app/@jackwang): Senior Software Engineer, Scale AI
- [Steve Liu](https://himalayas.app/@steveliu): Senior Software Engineer, Abridge
- [Sonoi Ogbuefi](https://himalayas.app/@sonoiogbuefi): Machine Learning Engineer Applied AI, FalconX
- [Somesh Panchal](https://himalayas.app/@someshpanchal): Machine Learning Engineer, Qorvo, Inc
- [Narasimha Chari Nanchella](https://himalayas.app/@narasimhacharinanche): AI/ML Engineer, NVIDIA
