~/resume

Eugene Vincent

I build production infrastructure — and the AI that runs on it. Looking for DevOps and AI internships where reliability and cost per task are the metrics that matter.

Aurora, ILCS @ UIC, third yearAZ-900 certified

Right now, on my rack 95.2%cluster uptime 20server TPS live

Summary

Third-year CS student who runs a single-node Kubernetes cluster the way a team runs production: every deployment declared in Git, every service scraped and alerted on, and every cost measured rather than estimated. Most of my work sits where infrastructure meets applied AI — most recently reproducing an NVIDIA research result about replacing large models with small ones, using my own agent telemetry as the dataset.

Selected work

LLM Orchestrator

Applied AI · Python
  • Reproduced NVIDIA Research's “Small Language Models are the Future of Agentic AI” end to end, running their six-step LLM→SLM conversion procedure against my own logged agent traffic rather than a public benchmark.
  • Built a hindsight replay over the telemetry ledger that measured a 66% ceiling on locally-servable spend, then graded a 35B model against the same tasks to land a defensible 57% — inside the paper's predicted 40–70% band, on a corpus it never saw.
  • Raised routing quality to 0.810 against a 0.286 random-assignment floor by combining keyword classification with a local-model rescue pass.
  • Published the method with its caveats stated, including an estimate that moved 45%→24% once a dominant session was sampled more than once.
  • Python
  • llama.cpp
  • Claude API
  • evals + telemetry

Homelab platform

Infrastructure · Kubernetes
  • Run a single-node k3s cluster as a production environment: GitOps delivery through ArgoCD app-of-apps, so no service is deployed by hand.
  • Instrumented every workload with Prometheus, Grafana and Loki, plus Istio mTLS between services and cert-manager for TLS issuance.
  • Secrets stay out of Git via External Secrets backed by Azure Key Vault; 7 alert rules across 5 services page a Discord incident bot before users notice.
  • Total infrastructure cost: $0/month, on hardware under my desk — with uptime published live rather than asserted.
  • k3s
  • ArgoCD
  • Prometheus
  • Grafana
  • Loki
  • Istio

MeshWatch

Observability · Cost engineering
  • Delivered full-stack observability — metrics, logs, distributed traces and AI incident analysis — for $5.12/month, about 60% under the serverless equivalent.
  • Added Tempo tracing and a local Phi-3 model that summarises incidents, keeping analysis on-premises instead of shipping logs to a vendor.
  • Istio
  • Tempo
  • Ollama
  • Grafana

Aria — iOS music player

iOS · Swift
  • Built a native SwiftUI player from scratch with zero third-party dependencies, including a real 10-band parametric EQ on AVAudioEngine.
  • Backed it with a Python service that resolves and caches streams, and covered the app with 364 automated tests across 39 files, currently passing with 0 failures.
  • Swift
  • SwiftUI
  • AVAudioEngine
  • FastAPI
  • XCTest

Serverless health checks

Cloud · Python
  • Wrote Azure Functions that probe homelab services every 15 minutes and process incident events off a Service Bus topic, with Pydantic-validated payloads.
  • Cut alert fatigue with a 5-minute dedup window that collapses repeat failures into a single Discord notification instead of a storm.
  • Azure Functions
  • Service Bus
  • Pydantic
  • aiohttp

Skills

Infrastructure

Kubernetes (k3s), ArgoCD / GitOps, Istio service mesh, cert-manager, External Secrets, Docker, Linux, Cloudflare Tunnel

Observability

Prometheus, Grafana, Loki, Tempo, PromQL, alert rule design, JMX and RCON exporters, incident response

Cloud & edge

Azure Functions, Service Bus, Key Vault, Cloudflare Pages / Functions / KV, GitHub Actions CI/CD

Languages

Python, Swift, JavaScript, Bash, SQL, YAML

Applied AI

Local inference with llama.cpp, model routing and cost control, evaluation harness design, telemetry pipelines, QLoRA fine-tuning

Practice

Test-driven development, pytest and XCTest, accessible front-end (WCAG 2.1), technical writing

Education & certification

University of Illinois Chicago — BS Computer Science

Third year

AZ-900 — Microsoft Azure Fundamentals

Certified