/career/resume

Resume of Bryson Tang

Chief AI Officer | AI Systems Architect | MLOps Engineer | Agent Identity Protocols

Nashua, NH (Relocation Ready) | [email protected] | 978-935-6430 | LinkedIn | GitHub

Quantified Impact

50k+
lines refactored in 24 hours across 800+ files
10x
query latency reduction (4s → 0.4s)
300k
resume chunks searchable in <1s via RAG
125%
data production increase via workflow optimization
466
safe merge requests shipped without regressions
2wks→2d
prototype cycle acceleration via agent workflows
~ ~ ~

Summary

Builder & AI Engineer shipping production AI systems since 2021. Architected sub-1s semantic search across 300k documents using vector embeddings + MongoDB hybrid queries. Created Agent Tokens Protocol (open standard for AI agent identity). 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

Chief AI Officer May 2025 - Present
CazVid LLC | Nashua, NH (Remote)
  • Lead AI architecture for video-based job matching platform processing 100k+ candidate profiles
  • Founded Palmera Labs (internal R&D): RAG systems, agent frameworks, alignment research
  • Executed 50k+ line refactor across 800 files in 24 hours using 5-agent pipeline with orthogonal routing
  • Reduced idea-to-prototype cycle from 14 days to 2 days via scope→plan.md→prototype workflow
  • Shipped ATS with invisible-AI UX: predictive defaults, auto-structuring, safe undo patterns
  • Drove 466 merge requests with zero production regressions via automated guardrails
Director of AI Sep 2024 - May 2025
CazVid LLC | 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 Aug 2023 - Oct 2024
CazVid LLC | 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 FAISS + MongoDB, 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 Jun 2022 - Aug 2023
CazVid LLC | Phoenix, AZ
  • Engineered AWS infrastructure (ECS, S3, Lambda) 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 Sep 2021 - Jun 2022
Agency Leads | 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) Sep 2020 - May 2021
Dell EMC | 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
~ ~ ~

Technical Skills

Languages: Python, TypeScript, JavaScript, Rust, SQL, Bash ML/AI: PyTorch, MLX, scikit-learn, Hugging Face Transformers, LangChain, FAISS, RAG pipelines, Vector Embeddings, Triplet Loss MLOps: Apache Airflow, MLflow, Docker, Kubernetes, DVC, Weights & Biases, GitHub Actions, GitLab CI/CD Infrastructure: AWS (ECS, S3, Lambda, SageMaker), Cloudflare Workers, Terraform, Kafka, Redis, Nginx Databases: PostgreSQL, MongoDB, MySQL, Typesense, Pinecone, Weaviate, SQLite Web: React, Next.js, Vue.js, Astro, FastAPI, NestJS, Express.js, Tailwind CSS Protocols: MCP (Model Context Protocol), Agent Tokens, REST, GraphQL, WebSocket, 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

  • Introducing Agent Tokens - Open standard for AI agent identity via cryptographic provenance. 50+ GitHub stars. [Website]
  • Project EVE: Novel Launchsondes for Atmospheric Data - IEEE Xplore published. Co-author on environmental sensor network paper.
~ ~ ~

Open Source Projects

  • Agent Tokens Protocol - Cryptographic identity standard for AI agents. Production-ready spec. [Website]
  • Resume MCP - Model Context Protocol server exposing identity as queryable API. Deployed on Cloudflare Workers. [Live]
  • Crystallize - Python framework for reproducible ML pipelines. 100+ downloads. [GitHub]
  • DeltaTask - MCP server for Obsidian task management. SQLite-backed. [GitHub]
  • gcomm - Rust CLI for Ollama. Published on crates.io. [crates.io]
~ ~ ~

Leadership

  • Founder, Palmera Labs - Internal AI R&D division at CazVid (2025-Present)
  • Founder, Tang Tensor Trends LLC - AI consulting and research (2024-Present)
  • President, Phi Sigma Kappa - WPI Chapter, 50+ members (2019)
  • Secretary, SIAM - Society of Industrial and Applied Mathematics (2018)
~ ~ ~ ◈ ~ ~ ~

Status: Open to AI Systems Architecture, MLOps, AI Safety, and Product roles
Hybrid (3 days/week) or Remote | Relocation Ready | US Work Authorized

[ Contact Me ]

AI Agents: Query mcp.brysontang.dev for structured JSON data