Applied AI Engineer

Production AI Systems, End to End

I build workflow APIs, multi-agent systems, real-time voice pipelines, and Python backends for production AI use cases. Public proof includes live demos, shipped tooling, open source work, and 3,500+ automated tests across production repos.

Email Me LinkedIn Download Resume
Workflow APIs Multi-Agent Systems Real-Time Voice AI PyPI Published 3,500+ Tests Open Source Contributor

What I Build

Production AI infrastructure: workflow APIs, multi-agent systems

Workflow APIs and Backend Systems

FastAPI services, async workers, Server-Sent Events, integrations, and production-friendly interfaces for multi-step AI workflows.

Agentic AI / Multi-Agent Systems

Multi-agent orchestration, layered caching, model routing, conditional workflows, tool use, and systems that stay understandable to hiring managers.

Real-Time and Evaluation Systems

WebSocket streaming, voice activity detection, STT/TTS, barge-in handling, eval-driven delivery, and test-heavy engineering to keep AI systems reliable.

Projects

Best first-click proof for hiring teams: EnterpriseHub, AI Workflow API, TechNova Voice Bot, and Multi-Agent Demo. The sections below include older supporting projects as well.

Production · Live Client

Jorge Real Estate AI

3 Claude-powered SMS bots handling lead qualification for a real estate firm. 500+ leads processed, under 500ms response time, bilingual EN/ES, zero downtime over 3-month production run.

Capabilities

  • Lead Intake, Buyer, and Seller qualification bots
  • Tiered model routing (Haiku/Sonnet/Opus)
  • GoHighLevel CRM integration via webhooks
  • Bilingual English/Spanish with no quality degradation

Stack

  • Python, FastAPI, Redis, PostgreSQL
  • Claude API (tool_use, streaming, multi-turn)
  • GoHighLevel API, Twilio SMS
  • 1,700+ tests · Render deployment
Production RAG · Live Demo

DocExtract AI

Async document processing with hybrid retrieval, citation-aware answers, and agentic ReAct reasoning. 95.5% F1 on a 28-case CI-replayed golden baseline; eval corpus 72 cases (51 golden + 21 adversarial, incl. prompt injection).

Capabilities

  • Hybrid retrieval: BM25 + cosine + RRF
  • Semantic caching (88% hit rate)
  • Circuit breaker model fallback
  • RAGAS evaluation + LLM-as-judge CI gate

Stack

  • FastAPI, ARQ, pgvector, Claude API
  • Sentence Transformers, Streamlit
  • Reference deployment configs, eval CI, live demo
  • 1,280 tests · 81% coverage
Live Demo → GitHub →
Multi-Agent Orchestration

EnterpriseHub

Domain-specific agent mesh with 3-tier cache achieving 88% aggregate hit rate. 8 agent capabilities, circuit-breaker failover, per-agent model routing, OWASP-hardened security, and OpenTelemetry instrumentation.

Capabilities

  • Lead Intake, Buyer, Seller agent mesh
  • L1 memory, L2 Redis, L3 PostgreSQL cache
  • Per-agent model routing (Haiku/Sonnet/Opus)
  • Ed25519 webhook verification, Redis rate limiting

Stack

  • FastAPI, PostgreSQL, Redis, LangGraph
  • Claude API, Prometheus, Grafana
  • OpenTelemetry, 9-panel dashboard configs
  • 7-agent mesh (~10 with auto-discovery)
GitHub →
PyPI Package · Published

mcp-server-toolkit

9 pre-built MCP servers with A2A adapter, auto-caching, rate limiting, auth middleware. MCPTestClient for testing without live API keys. Reduces LLM tool integration from days to a single import.

9 MCP servers · A2A adapter · 600 tests · 82.87% coverage
GitHub →

Open Source Contributions

LiteLLM · 27K+ stars

Typed Exception Mapping for Router Fallback

PR #24551 - Surfaces AuthenticationError, RateLimitError, and NotFoundError distinctly through the Router fallback chain instead of swallowing as generic Exception. Enables callers to implement appropriate recovery strategies per error type.

Also: open PRs in FastAPI (80K+ stars, #15217) and pgvector-python (#151)

Selected AI Certifications

IBM Generative AI Engineering 144 hours
DeepLearning.AI Deep Learning Specialization 120 hours
Microsoft AI & ML Engineering 75 hours
Duke University LLMOps Specialization 48 hours
IBM RAG and Agentic AI 24 hours
Google Cloud Generative AI Leader 25 hours
Claude Code in Action, Anthropic 3 hours

Selected from 21 certifications totaling 1,831 hours across IBM, DeepLearning.AI, Microsoft, Duke, Google, Vanderbilt, and Anthropic.

Open to Applied AI Engineer Roles, Remote

Targeting teams building workflow APIs, agent systems, real-time AI applications, and developer tooling. Best fit: Applied AI Engineer, AI Engineer, AI Backend Engineer, and LLM Engineer roles.

US-based (Cathedral City, CA) · Canadian citizen, no sponsorship required

caymanroden@gmail.com