mlc-llmAMD · gfx1100
Qwen3-8B-abliterated-q4f32_1-MLC
106.0tok/s
8 GiB VRAM
Integration architecture and reliability systems
Cody Blevins
I help teams make integrations predictable: clear contracts, readable operations, and delivery paths that stay calm when the system gets messy.
Integrations Manager at Devoted HealthHealthcare interoperabilityPlatform reliability
Current role
Devoted Health
Integrations Manager
Implementing and delivering healthcare integrations across data specs, partner workflows, and operational handoffs.
13+ years
Healthcare IT
Integration, interoperability, and reliability roles
100%
SLA adherence
Production support and reliability ownership
~30%
Support response
Case monitoring and escalation workflow improvements
Start Here
Start with what you need
Seven doors into the same site — pick by what you're trying to get done.
Services
See engagement shapes, timelines, and where I add leverage.
Products
See where each product surface fits and why it matters.
Playground
Run hands-on validation and workflow tooling.
Writing
Read implementation notes and case studies.
About
See professional background and operating principles.
Resume
Use the concise version for scope, systems, and delivery history.
Contact
Talk about an engagement, collaboration, or a thorny system.
Professional Focus
Integration Leadership with Operator Instincts
I bridge architecture, implementation, and operations so teams can ship integrations that stay reliable in production.
13+Years in Healthcare IT
Healthcare Integrations
Designed and operated healthcare API integrations across HL7v2 and FHIR workflows.
Delivered healthcare data exchange across implementation and operational roles
~30%Faster Support Response
Reliability & Operations
Improved case monitoring, escalation handling, and API support operations.
Sustained 100% SLA adherence while improving support response time
Multi-siteData Center Migration
Technical Program Delivery
Led complex migration and upgrade programs with clear risk and dependency management.
Delivered migration and disaster-recovery planning for critical services
Proof of worksnapshot
Measured on the homelab runtime
FlexInfer is the private inference platform I keep running on real hardware. These results come from the cluster benchmark records, not a sample dataset.
Snapshot verified
106.0tok/s recorded peak
mlc-llmAMD · gfx1100
Qwen3-14B-q4f16_1-MLC
82.4tok/s
16 GiB VRAM
mlc-llmAMD · gfx1100
Qwen3-14B-abliterated-q4f16_1-MLC
75.0tok/s
16 GiB VRAM
teiCPU
BAAI/bge-large-en-v1.5
203.3emb/s
2 GiB memory
diffusersAMD · gfx1100
stabilityai/sdxl-turbo
61.6img/min
10 GiB VRAM
Snapshot scope. These legacy benchmark-result records preserve backend, hardware class, memory, and throughput, but not prompt, batch, or sample counts. Treat them as operational baselines, not a cross-vendor leaderboard.
Inspect the source recordsSelected Work
Projects & Labs
A representative slice of the systems, tools, and experiments I keep running in public.
Writing
Interoperability, Reliability, and Delivery
Practical notes from healthcare integrations, platform reliability work, and cross-functional delivery.
April 20, 2026
The First 90 Days: Introducing AI-Assisted Dev to a New Team
How I would roll out AI-assisted development on a team that has not standardized: what to do in week one, what to earn the right to argue about later, and what almost always goes wrong.
agentsai-assisted-devadoptionteam-practicemethod
April 20, 2026
A One-Page AI Usage Policy That Actually Works
A short, adoptable AI usage policy for engineering teams: what to put on the page, what to leave off, and why the policy matters less than the habits it makes explicit.
ai-assisted-devpolicyteam-practicegovernancemethod
Let's Solve the Hard Integration Work
If your team needs stronger integration architecture, better operational signal, and faster incident recovery, I'd love to help.