Steffan Troxel

AI Software Engineer
Cape Girardeau, MO (remote) · sjtroxel@protonmail.com · github.com/sjtroxel · linkedin.com/in/sjtroxel

AI Software Engineer building production multi-agent and RAG systems in Python and TypeScript, all deployed and live on Railway and Vercel. Systems ground their outputs in retrieved evidence with citations, score confidence from observable signals, hand off to a human when they should, and are gated by evaluation suites in CI. Works spec-first with AI-assisted development (Claude Code and other agentic coding tools), pairing velocity with strict typing and 1,800+ automated tests.

Projects

Patchwork Assurance — grounded US AI-regulation compliance tool — patchworkassurance.com
Heritage Odyssey — family-history RAG platform with voice narration — heritage-odyssey.vercel.app
Wildlife Sentinel — 24/7 autonomous wildlife crisis intelligence — wildlife-sentinel.vercel.app
Asteroid Bonanza — multi-agent asteroid intelligence platform — asteroid-bonanza.vercel.app

Also live: Poster Pilot (multimodal RAG over 5,000+ historical posters, CLIP + Reciprocal Rank Fusion), SoilProve (fertilizer-prescription tool, multi-provider LLM failover, built solo in 5 days), and ChronoQuizzr (geography trivia, adversarial two-agent clue-verification pipeline).

Experience

AI Software Engineer · Self-directed · Remote · January 2026 – present
Designed, built, and operate the production AI systems above: agent orchestration, grounded RAG and vector search, evaluation pipelines (golden datasets, LLM-as-judge), streaming APIs, an MCP server, and cost-aware multi-model routing, in Python and TypeScript.
Student Software Engineer (Apprenticeship) · Codefi · Remote · January 2025 – present
Year-long full-stack bootcamp (JavaScript, TypeScript, Angular, React, Ruby on Rails), followed by Codefi's AI Skills track: Prompt-to-Product and the production AI engineering Masterclass.

Education

Skills

AI / LLM: Retrieval-Augmented Generation (RAG), multi-agent orchestration, LLM-as-judge evaluation, golden datasets, Model Context Protocol (MCP), LLM APIs (Anthropic, OpenAI, Google), LangGraph, vector databases (Chroma, Pinecone, pgvector), prompt engineering, spend-safety

Languages & backend: Python (FastAPI, Streamlit), TypeScript (strict mode), Node.js, Express 5, Ruby on Rails, PostgreSQL, PostGIS, Redis Streams, SSE streaming

Frontend: React, Angular, Next.js, Tailwind CSS

Testing & delivery: pytest, Vitest, Playwright, GitHub Actions CI, Docker, Railway, Vercel