Kategorien durchsuchen
Entdecken
Fiverr Pro
Deutsch
$
USD
I will build python fastapi backend, comfyui serverless api for vibe coded apps
DevOps Engineer
Über diesen Service
Turn your ComfyUI workflow or AI idea into a real, working Python API.
I am a DevOps and backend engineer. I take AI workflows and half-finished apps and turn them into production services that hold up under real traffic.
WHAT I BUILD
ComfyUI workflows deployed as serverless APIs on RunPod, Replicate or fal
FastAPI and Flask backends: auth, job queues, webhooks, S3 storage, rate limits
Python automation: batch generation, custom ComfyUI nodes, prompt API scripting
Docker images and GitHub Actions CI/CD pipelines
Deployment to AWS, GCP or your own VPS with Nginx, SSL and monitoring
BUILT IT WITH AI AND NOW IT WILL NOT SHIP
If you built something with Claude Code, Cursor, Lovable, Bolt or Replit and it will not deploy, leaks API keys, or falls over under load, I will review it, fix the backend and ship it properly.
WHAT YOU GET
Clean source code, a Dockerfile, API documentation, an env template, and a walkthrough of how to run and scale it yourself.
I am available 24/7 and I work US hours. Send me your workflow JSON or repo link and I will scope it honestly before you order.
Lerne DevOps Engineer kennen
DevOps Engineer
Senior AI DevOps Engineer: AWS, Kubernetes, ComfyUI APIs, DevSecOps
- AusIndien
- Mitglied seitDez. 2017
- Letzte Lieferung1 Jahr
Sprachen
Hindi, Englisch
AI DevSecOps and Cloud Infrastructure Engineer, 4 years building production systems. I ship what most AI projects are missing: the infrastructure underneath.
I work with AWS and EKS, Terraform, Docker and CI/CD (Jenkins, GitHub Actions), secured with IAM, WAF, SSL/TLS and Secrets Manager. On the AI side I deploy ComfyUI, Stable Diffusion, Flux and Wan as serverless APIs on RunPod and AWS, wrapped in Python and FastAPI backends, monitored with Grafana.
Available 24/7 on US hours. Clear updates, documented handover, and I do not disappear mid-project.
Meine weiteren Dienstleistungen im Bereich KI-Entwicklung
FAQ
Do I need a RunPod or AWS account?
Yes. The deployment goes on your own account so you keep full ownership and control the billing. I set it up and walk you through it step by step.
Do I get the source code?
Always. You get the full repository, Dockerfile and API docs, so you or another developer can maintain it later.
What does the API actually return?
A clean JSON endpoint. You POST your parameters, get a job ID back, then poll or receive a webhook with the finished image, video or file URL.
My app was built with Lovable or Claude Code. Can you fix it?
Yes. Send me the repo. I review the backend, fix what is broken, move secrets out of the frontend, and deploy it properly.
Can you handle video models like Wan or LTX?
Yes. Wan 2.2, LTX, AnimateDiff and image to video pipelines all run as serverless endpoints. They need larger GPUs, which affects your running cost, and I tell you that up front.
How much will the GPU cost to run?
It depends on your model and traffic. I give you a realistic cost estimate per 1000 generations before we start, so there are no surprises on your cloud bill.
What are your working hours?
I am available 24/7 and I work US hours, so we can talk in your timezone. I usually reply within an hour.
Will you sign an NDA?
Yes. Your workflows, prompts and code stay confidential, and I do not reuse client work.
