Gawaine O'Gilvie
Senior Software Engineer
Building AI-powered products and scalable backend systems.
- Built internal platforms used by engineering teams at scale
- Developed AI-powered applications (LLMs, RAG pipelines, vision-language models)
Currently focused on the intersection of AI systems and backend infrastructure — building production-grade tools that put language models to work at scale. Most energized by green-field projects, platform problems, and work that requires both systems thinking and AI literacy. Open to full-time roles and contract engagements where technical depth matters.
AI & Machine Learning Projects
Signal to Alpha — Options Trading Platform
Problem
Retail traders lack systematic tools to capture unstructured Discord trade callouts, execute them across multiple brokers, and analyze performance with AI-powered critique
Solution
Built a full-stack options trading platform: 4-stage NLP parsing pipeline (classify → extract → normalize → score), multi-broker execution layer (Schwab OAuth 2.0 + Webull HMAC-SHA1) with Fernet-encrypted token storage, 4 automated trading strategies with shared risk guards (GFV protection, ATR gate, HTF regime filter), and AI trade critique via Claude with tiered market data and per-user rate limiting
Impact
End-to-end trade lifecycle from Discord callout to P&L analytics, tax estimation, and journal — 189 pytest tests, live WebSocket price streaming to all connected clients, real-time bot config reloads without restarts
DocSage — RAG Document Intelligence Platform
Live Demo →Problem
Teams waste hours manually reviewing large document sets with no semantic search, structured traceability, or grounded AI answers tied to real source passages
Solution
Built a production RAG pipeline: multi-format ingestion (PDF with dual-parser fallback, HTML, Markdown), 512-char sliding-window chunking, OpenAI text-embedding-3-small embeddings stored in pgvector with an HNSW index, cosine similarity retrieval via a custom SQL stored function, and GPT-4o synthesis with Pydantic-validated structured output and retry logic via tenacity — deployed on AWS RDS PostgreSQL + Render + Vercel
Impact
Live at docsage.phoenix7.dev — every response returns exact citations, token counts, and USD cost; 37-test async pytest suite covering the full RAG stack from ingestion to LLM retry paths
Problem
Debugging production incidents required hours of manual log parsing to identify root causes
Solution
Built a full-stack app (Next.js + FastAPI) that analyzes production logs using OpenAI GPT-4 to identify errors, cluster patterns, and surface root causes with actionable remediation steps
Impact
85% reduction in debugging time for production incidents and CI/CD failures
PR AI Assistant
GitHub →Problem
Code reviews created bottlenecks, delaying PRs and missing subtle behavior changes or risks
Solution
Built a GitHub Actions bot that automatically reviews pull requests using OpenAI GPT-4, analyzing git diffs and providing structured summaries with behavior changes, risks, and validation steps
Impact
Automated intelligent code reviews on every PR, catching risks before human review
Core Engineering Projects
Developer Platform Tooling
Problem
Engineers lacked standardized workflows for testing and deployment across distributed services
Solution
Built internal tooling to streamline CI/CD, contract validation, and deployment workflows for cloud services
Impact
Reduced deployment time by 40% and eliminated 85% of contract violations across 10+ microservices
Enterprise Inventory Management Platform
Problem
Client needed a scalable system for managing inventory with QR scanning, media uploads, and multi-role access control
Solution
Delivered 25+ user stories including authentication, QR code scanning, admin console, and media upload functionality on a modern React/TypeScript stack
Impact
Full platform delivered on time with role-based access, real-time updates, and print-optimized QR labels
Experience
Freelance Consulting
Senior Full-Stack Engineer & Technical Consultant
2025 - Present
- Built a full-stack options trading platform (Signal to Alpha) with live broker execution, automated strategy bots, and AI trade critique — Next.js 15 / FastAPI / PostgreSQL / Supabase Auth — end-to-end trade lifecycle from Discord callout ingestion to P&L analytics and tax estimation
- Engineered a 4-stage NLP alert parsing pipeline that classifies, extracts, normalizes, and scores unstructured Discord trade callouts into structured OCC option symbols — confidence scoring routes low-quality alerts to a human review queue rather than auto-execution
- Integrated two institutional broker APIs (Schwab OAuth 2.0 and Webull HMAC-SHA1) with Fernet-encrypted token storage, paper trading mode, and a unified order abstraction layer — zero plaintext secrets at rest
- Designed a live-reloadable bot configuration system using a PostgreSQL singleton read on every scheduler tick — risk parameters (stop loss, max positions, GFV guards) take effect in real time during live market sessions without restarts
- Built a real-time WebSocket price streaming layer maintaining persistent connections to Schwab and Webull broker streamers, fan-outing normalized price events to all connected frontend clients — eliminates polling for live P&L and position updates
- Delivered AI-powered trade critique using the Claude API with structured prompts combining parsed callout + live option chain data; per-user rate limiting (slowapi) and TTL caching reduce API cost; yfinance fallback serves free-tier users
Sonos, Inc.
Senior Software Engineer (Cloud Team)
2017 - 2025
- Migrated 10+ applications to AWS EKS, reducing infrastructure costs by 40% through optimized containerization and resource allocation
- Built Lambda/S3 data pipelines processing millions of events with robust error handling and batch processing for reliable data ingestion
- Developed automation systems that reduced Kubernetes migration time by 80% and streamlined daily deployments for cloud services
- Built developer productivity platforms using React and TypeScript, increasing engineering team satisfaction by 30%
- Mentored junior engineers on TypeScript best practices, AWS architecture patterns, and Kubernetes deployment strategies
Nuance Communications
Software Engineer
2014 - 2017
- Engineered real-time WebSocket services in Python (Flask, Bottle) handling high-throughput voice recognition traffic in production
- Built and maintained microservices and RESTful APIs supporting speech and analytics workflows across internal and external systems
- Developed monitoring dashboards that improved incident response time by 40% with real-time visibility into system health
- Collaborated with data scientists to optimize speech recognition models and improve accuracy metrics
Technical Skills
Languages
Backend & Systems
AI / ML
Cloud & Infrastructure
Frontend
Databases & Observability
Education
Master of Science, Data Science
University of Texas at Austin
Austin, TX
- Advanced coursework in Machine Learning, Statistical Analysis, and Data Engineering
- Specialization in predictive modeling and big data analytics
Bachelor of Science, Computer Engineering
Northeastern University
Boston, MA
- Focus on Software Engineering and Systems Architecture
- Coursework: Data Structures, Algorithms, Embedded Systems, Computer Networks
Work With Me
I help teams build and ship faster. Available for contract and consulting engagements.
- Build AI-powered applications (LLMs, RAG pipelines, intelligent automation)
- Design scalable backend systems and cloud infrastructure
- Improve developer velocity, CI/CD, and platform tooling
Contact
Available for full-time roles and contract / consulting work • Open to remote or hybrid
Outside of Engineering
Muay Thai — discipline and consistency
Cooking — experimentation and iteration
Vinyl — appreciation for craft and detail