# Resume of Bryson Tang

Founder, Syntropy Systems | Research Engineer | AI Systems Architect

Nashua, NH · brysontang@gmail.com · 978-935-6430 · [LinkedIn](https://www.linkedin.com/in/bryson-t-datascience/) · [GitHub](https://github.com/brysontang)

## Quantified Impact

- **525K**: requests/month on production ML infrastructure
- **150k**: lines → agent-native codebase
- **10x**: query latency reduction (4s → 0.4s)
- **300k**: resume chunks searchable in <1s via RAG
- **466**: safe merge requests shipped without regressions
- **2wks→2d**: prototype cycle acceleration via agent workflows

## Summary

Founder of Syntropy Systems, building Elwood, an AI worker, and open-sourcing the tooling that tests agents and schedules their experiments: windtunnel (agent reliability bench), pit (a prediction market that schedules experiments), and whirr (local experiment orchestration). 10 years building data and ML systems — from high school SQL dashboards to production infrastructure handling 525K requests/month. Interpretability on consumer hardware: a sparse-autoencoder replication of Golden Gate Claude on Qwen2.5-1.5B and a backward "ghost-token" Jacobian lens on Qwen3-0.6B. Research background: 70-paper literature synthesis on AI safety, backpropagation from the 1986 Rumelhart paper, research mentorship designing paper curricula. Architected sub-1s semantic search across 300k documents. Created the Agent Tokens protocol. Built 5-agent orchestration pipeline handling 150k+ line edits with zero regressions. WPI Data Science graduate (3.75 GPA, High Distinction). BlueDot AI Safety Alignment certified.

## Experience

### Founder · Syntropy Systems, Inc.
*Jan 2026 - Present · Nashua, NH*

- Building **Elwood**, an AI worker that gives teams leverage over the tools they already use, and asks for a go-ahead before doing anything new
- Open-sourced the agent testing and experimentation stack: **windtunnel** (reliability bench for tool-using agents; 19 releases, on PyPI as windtunnel-bench), **pit** (a prediction market that schedules experiments), and **whirr** (local experiment orchestration)
- Independent interpretability research on consumer hardware: replicated Anthropic’s **Golden Gate Claude** with a sparse autoencoder on Qwen2.5-1.5B, and extended Anthropic’s Jacobian lens with a backward “ghost-token” lens

### Chief AI Officer · CazVid LLC (Bootstrapped, ~20 employees)
*May 2025 - Dec 2025 · Nashua, NH (Remote)*

- Architect **Kern** ML infrastructure (525K requests/month): event-driven pipelines, probabilistic classification, embedding systems, evaluation frameworks
- Design AI systems using frontier models; evaluate tradeoffs between approaches (cost, latency, accuracy) and select architectures that match business constraints
- Transformed 150k-line legacy codebase into agent-native code: 1400 lint fixes → 900 type resolutions → 300-test suite. Agentic coding now works like greenfield.
- Founded **Palmera Labs** (internal R&D): RAG systems, agent frameworks, fast-weight plasticity research
- Technical leadership: onboard 7-engineer team on AI coding agents, translate CEO/COO requirements into technical roadmaps
- Drove 466 merge requests with zero production regressions via automated guardrails

### Director of AI · CazVid LLC
*Sep 2024 - May 2025 · Nashua, NH*

- Achieved sub-1s full-text search across 300k resume chunks via LLM/RAG + MongoDB hybrid filters
- Architected **Kern ML service**: FastAPI intake → Kafka queue → Redis state → NestJS/Pusher delivery
- Built universal matching algorithm using triplet loss embeddings + hybrid vector/text search
- Created no-code interface enabling non-engineers to deploy Codex-generated branches to production
- Synced GitLab CI/CD with GitHub Actions enabling repo-level context for AI agents

### Senior Software Engineer / AI Specialist · CazVid LLC (Bootstrapped, ~20 employees)
*Aug 2023 - Oct 2024 · Phoenix, AZ*

- Integrated ChatGPT API for automated client workflows, reducing response latency by 60%
- Built RAG-powered support desk handling 500+ daily queries with 94% resolution rate
- Designed vector-based matching algorithms using MongoDB Atlas Vector Search, improving match accuracy 35%
- Managed Apache Airflow pipelines processing 10k+ documents/day with 99.9% data consistency
- Maintained AWS ECS/Terraform infrastructure supporting $50k/mo cloud budget at 99.5% uptime

### Software Engineer / Data Scientist · CazVid LLC (Bootstrapped, ~20 employees)
*Jun 2022 - Aug 2023 · Phoenix, AZ*

- Engineered AWS infrastructure (ECS, S3) supporting 10k+ DAU with auto-scaling
- Architected web platform extending mobile app, increasing user engagement 40%
- Led post-acquisition technical integration: unified CI/CD, consolidated 3 codebases into 1

### Full Stack Engineer / Junior Data Scientist · Agency Leads
*Sep 2021 - Jun 2022 · Manchester, NH*

- Built Vue.js + Express.js data entry platform from scratch, processing 50k+ records
- Reduced Typesense query latency from 4s to 0.4s (10x improvement) via index tuning
- Increased data production 125% by implementing work classification specializations
- Deployed AWS ECS infrastructure with Terraform enabling zero-downtime deployments
- Created Tableau dashboards driving $2M+ in data-informed sales decisions

### AI/ML Capstone Project (MQP) · Dell EMC
*Sep 2020 - May 2021 · Worcester, MA*

- Built predictive model for hardware failure detection using deep learning on log data
- Applied Chi-Squared + Pearson correlation for feature selection across 500+ variables
- Presented weekly to Dell engineers; model deployed for internal diagnostic testing

## Early Experience

### Research Intern · WPI Computer Science Dept
*Jun 2020 - Aug 2020 · Worcester, MA*

Built COVID-19 demographic dataset aggregating UN, WHO, and Johns Hopkins data. Wrote Python pipelines, hosted on MySQL, published to Kaggle for research community.

### Software Engineering Intern · CyberSN
*Aug 2017 - Jan 2020 (2.5 years) · Boston, MA*

Full stack development on internal sales tooling (Blitz). Rapid prototyping, documented codebase architecture. Attended DEF CON 2019 (company-sponsored).

### Data Intern · Biscom
*May 2015 - Jul 2017 (2 years) · Westford, MA*

First technical role at age 16. SQL queries on production databases, built user analytics dashboards in Excel, presented findings to company president and engineering team.

## Technical Skills

- **Research:** PyTorch, MLX, NumPy, scikit-learn, Hugging Face, distilabel, Jupyter, matplotlib, LaTeX
- **Languages:** Python, TypeScript, JavaScript, Go, Rust, SQL, Bash
- **ML/AI:** LangChain, RAG pipelines, Vector Embeddings, Triplet Loss
- **MLOps:** Apache Airflow, MLflow, Docker, Kubernetes, Weights & Biases, GitHub Actions
- **Infrastructure:** AWS (ECS, S3), Cloudflare Workers, Terraform, Kafka, Redis
- **Databases:** PostgreSQL, MongoDB, Typesense, Pinecone, SQLite
- **Web:** FastAPI, React, Next.js, Astro
- **Protocols:** MCP (Model Context Protocol), Agent Tokens, REST, GraphQL, Nostr

## Education

### Worcester Polytechnic Institute (WPI) (May 2021)
- B.S. Data Science, Minor in Mathematical Sciences
- GPA: 3.75/4.0 · Graduated with High Distinction

### BlueDot Impact (June 2024)
- AI Safety Fundamentals: Alignment
- 12-week certification

## Publications & Research

- **AI Safety Compass** (2025): 70-paper literature review exploring model meta-alignment. Original survey methodology mapping where models sit on alignment/openness axes. [Paper](https://github.com/brysontang/ai-safety-compass/blob/main/paper/main.pdf)
- **Backprop Paper Replication** (2025): Hand-derived gradients from Rumelhart et al. 1986, implemented on Apple MLX. No AI assistance — just the paper and framework docs. [GitHub](https://github.com/brysontang/mlx-lab)
- **Introducing Agent Tokens** (2024): Open standard for AI agent identity and intent: signed, JWT-style tokens that declare what an agent is allowed to do. [Website](https://agenttokens.org)
- **Project EVE: Novel Launchsondes for Atmospheric Data** (2022): IEEE Xplore published. Co-author on environmental sensor network paper. [Paper](https://ieeexplore.ieee.org/document/9705814)

## Research Mentorship

**Summer 2025**: Designed and led intern research project investigating bias in embedding-based hiring systems.

Paper curriculum:

1. Language Models are Few-Shot Learners (GPT-3)
2. Chain-of-Thought Prompting Elicits Reasoning
3. ReAct: Synergizing Reasoning and Acting
4. Sparks of AGI: Early Experiments with GPT-4
5. Core Views on AI Safety: When, Why, What, How
6. Constitutional AI: Harmlessness from AI Feedback
7. The Superintelligent Will (Bostrom 2012)
8. Man is to Computer as Woman is to Homemaker? Debiasing Embeddings
9. Synthetic Data Generation: A Survey
10. Demystifying Embedding Spaces using LLMs
11. What are polysemantic neurons?

**Methodology:** Structured research board (hypotheses → experiments → paper draft), weekly syncs, "stay one week ahead" cadence.

**Output:** Unpublished paper applying utilitarian frameworks to LLM ethics, investigating gender bias in synthetic resume retrieval systems.

## Selected Projects

- **pit**: https://github.com/syntropy-systems-oss/pit
- **jacobian-lens**: https://github.com/brysontang/jacobian-lens
- **Golden Gate Qwen**: https://github.com/brysontang/golden-gate-qwen
- **ContextWars**: https://github.com/brysontang/ContextWars
- **AI Safety Compass**: https://github.com/brysontang/ai-safety-compass
- **crystallize**: https://github.com/brysontang/crystallize
- **agent-tokens**: https://agenttokens.org
- **fMCP**: https://github.com/brysontang/fmcp-spec
- **windtunnel**: https://github.com/syntropy-systems-oss/windtunnel
- **whirr**: https://github.com/syntropy-systems-oss/whirr
- **Kern**
- **resume-mcp**: https://github.com/brysontang/resume-mcp

Every project: https://brysontang.com/lab.md

## Leadership

- **Founder, Palmera Labs**: Internal AI R&D division at CazVid (2025)
- **Founder, Syntropy Systems, Inc.**: AI workers and open-source agent tooling (2024-Present)
- **President, Phi Sigma Kappa**: WPI Chapter, 50+ members (2019)
- **Secretary, SIAM**: Society of Industrial and Applied Mathematics (2018)

## Status

Building Syntropy full time · open to research collaborations

Based in Nashua, NH | US Work Authorized

Contact: brysontang@gmail.com

---

Markdown versions of every page: [Home](https://brysontang.com/index.md) · [The Lab](https://brysontang.com/lab.md) · [The Studio](https://brysontang.com/studio.md) · [The Archive](https://brysontang.com/archive.md) · [Resume](https://brysontang.com/resume.md) · [Guestbook](https://brysontang.com/guestbook.md)

AI agents are welcome to sign the guestbook: https://brysontang.com/guestbook.md