About

AI Engineer building Python and FastAPI LLM applications with retrieval, structured outputs, evaluation, and human handoff. Remote, US-based.

Who I Am

Based in the Inland Empire, California. My work centers on FastAPI backends, retrieval pipelines, evaluation harnesses, and public proof repositories. Client-facing operations experience still shapes how I scope work, communicate tradeoffs, and deliver under real constraints.

The proof on this site starts with named paid delivery for Acuity, then DocExtract, llm-reviewer-path, and mcp-server-toolkit on GitHub. Independent repositories are independent unless explicitly labeled paid.

What I Do

Production AI Delivery

Applied AI Systems That Ship

I build AI systems that have to work inside real workflows: RAG pipelines, agent workflows, FastAPI services, and evaluation gates. The paid Acuity engagement processed 500+ inbound leads. Public proof includes DocExtract at 95.5% weighted field-level accuracy, llm-reviewer-path, and mcp-server-toolkit on GitHub.

Backend And Reliability

Backend Systems Around LLMs

My strongest layer is the application layer around LLMs: retrieval, tool use, backend APIs, evaluation harnesses, caching, and operational debugging. Public proof includes DocExtract offline replay and an 80% CI coverage gate.

Stakeholder Ownership

Client-Facing Execution Without Role Drift

The strongest non-code part of my profile is delivery ownership. I came from 10 years of client-facing operations, so I am comfortable translating vague requirements into working systems, communicating constraints clearly, and making AI useful in live environments.

How I Work

1

Discovery

Understand your data, existing systems, constraints, and what "done" looks like. No scope creep - explicit deliverables before code starts.

2

Architecture

Design the system: data flow, component boundaries, API contracts, caching strategy, and deployment plan. You review before implementation.

3

TDD Build

Test-driven development. Tests first, then implementation, then refactor. CI runs on every push. You see progress in real-time via GitHub.

4

Delivery

Deployed with Docker, documented with examples, demo mode included. Handoff includes architecture docs, test coverage report, and a walkthrough call.

What I Bring to a Team

Strengths

  • Production Python AI systems with retrieval, orchestration, evals, and backend delivery
  • FastAPI, PostgreSQL, Redis, Docker, and API integration in real workflows
  • Proof stack: paid Acuity delivery, DocExtract offline replay, llm-reviewer-path, and mcp-server-toolkit on GitHub
  • Agent-security notes as a supporting differentiator, not the primary proof
  • 10 years of client-facing ops applied to technical delivery and stakeholder communication

Target Roles

  • AI Engineer / Applied AI Engineer
  • AI Backend Engineer / LLM Platform Engineer
  • Selective Forward Deployed Engineer roles
  • Remote, US-based

Stack

Backend & APIs

Python, FastAPI, REST APIs, PostgreSQL, Redis, Docker, GitHub Actions CI/CD, GoHighLevel CRM integration

Evaluation & Reliability

pytest, pytest-asyncio, RAGAS, LLM-as-judge, adversarial fixtures, GitHub Actions CI/CD, OpenTelemetry, structured logging

Retrieval & Data

SQL, PostgreSQL, pgvector, Redis, embeddings, semantic search, BM25, reciprocal rank fusion, Streamlit, Plotly

AI APIs & Orchestration

Claude API, OpenAI API, Gemini API, RAG pipelines, agent workflows, tool use, structured output, prompt engineering

Let's Talk

Open to remote AI Engineer, Applied AI, AI Backend, and LLM Platform roles. Selectively open to forward-deployed work that still centers on building and shipping real systems.