You will get an AWS Cost and Stability Audit for your AI/ML Workloads
Top Rated

Top Rated

Project details
5-day audit of your AWS infrastructure with focus on AI/ML workload efficiency. Read-only access, no production changes.
Who this is for:
Series A-C SaaS teams scaling on AWS, AI/ML teams preparing for production scale or investor due diligence, companies whose cloud bill grew faster than their infrastructure understanding.
What you get:
• Cost breakdown with top 10 savings opportunities (typically 20-40 percent reduction)
• Security review (IAM, VPC, exposed endpoints, secrets)
• Reliability gaps (single points of failure, backups, SLO risks)
• EKS and Kubernetes cluster health check
• AI/ML workload analysis (GPU utilization, inference cost, right-sizing)
• Written report with prioritized remediation roadmap
• 30-minute kickoff and handoff calls
Why me:
• 1M+ earned on Upwork, 100% JSS, 12,343 hours delivered
• AWS Certified Solutions Architect
• Previously Platform Engineer at Stack AI and Unstructured
• Recent: AWS backend for a Forbes-recognized VC-backed SaaS; 24K Senior Platform Engineer role (Python, AWS, K8s)
If the audit surfaces more than 1,500 per month in savings or a critical risk, it pays for itself the first month.
Who this is for:
Series A-C SaaS teams scaling on AWS, AI/ML teams preparing for production scale or investor due diligence, companies whose cloud bill grew faster than their infrastructure understanding.
What you get:
• Cost breakdown with top 10 savings opportunities (typically 20-40 percent reduction)
• Security review (IAM, VPC, exposed endpoints, secrets)
• Reliability gaps (single points of failure, backups, SLO risks)
• EKS and Kubernetes cluster health check
• AI/ML workload analysis (GPU utilization, inference cost, right-sizing)
• Written report with prioritized remediation roadmap
• 30-minute kickoff and handoff calls
Why me:
• 1M+ earned on Upwork, 100% JSS, 12,343 hours delivered
• AWS Certified Solutions Architect
• Previously Platform Engineer at Stack AI and Unstructured
• Recent: AWS backend for a Forbes-recognized VC-backed SaaS; 24K Senior Platform Engineer role (Python, AWS, K8s)
If the audit surfaces more than 1,500 per month in savings or a critical risk, it pays for itself the first month.
AI Algorithms
Large Language Model, Multimodal Large Language Model, Transformer ModelAI Applications
AI Chatbot, AI-Generated Code, AIOps, Conversational AIAI Development Language
PythonAI Tools
Hugging Face, NVIDIA AI Platform, PyTorch, TensorFlowAI Models
ChatGPT, GPT-4, LLaMA, Stable Diffusion, WhisperWhat's included $1,500
These options are included with the project scope.
$1,500
- Delivery Time 5 days
- Number of Revisions 1
- Database Integration
- MLOps
- Model Deployment
- Model Documentation
- Model Monitoring
- Model Testing & Optimization
60 reviews
(53)
(3)
(1)
(2)
(1)
This project doesn't have any reviews.
KF
Kara F.
Oct 2, 2025
Developer (DJ App/Desktop App Integration) Fix Bugs/Improve Performance
JM
Joseph M.
Sep 29, 2025
DevOps work to deliver a robust, highly available SaaS solution
Dmitrii is really, really talented, a hard worker, efficient and has a great attitude. He completed my project on-time.
TD
Troy D.
Sep 5, 2025
Needed: Senior Platform Engineer (Python, AWS, Kubernetes)
Great across the board for complex issues.
GS
Geoff S.
Aug 20, 2025
Qualtrics Coding Support for Bug Issues
Dmitrii was responsive and smart. Unfortunately we couldn't arrive at the solution I wanted which does not seem to be his fault.
CD
Connie D.
Aug 8, 2025
Sync Cal.com scheduling software with my Apple Calendar
Dimitri was fantastic to work with! Very efficient, kind, and fast!
About Dmitrii
AI/ML Infrastructure Architect | Production AI on AWS | 1M+ Earned
96%
Job Success
San Francisco, United States - 12:30 am local time
Previously: Platform Engineer at Unstructured (open-source document ETL for LLMs and RAG pipelines, YC-backed) and Stack AI (enterprise AI workflow platform).
100% Job Success Score | 12,343 hours delivered | 102 projects completed
AWS Certified Solutions Architect | San Francisco, CA
Recent engagements:
- Senior Platform Engineer (Python, AWS, Kubernetes) - 24K contract, 284 hours. Built GitOps pipeline reducing deployment cycles from 2 hours to 15 minutes. Maintained 99.9% uptime across production EKS clusters.
- AWS backend for a Forbes-recognized VC-backed SaaS. Architected infrastructure handling 10K+ concurrent API requests, reduced AWS costs by 35% through right-sizing and reserved instance optimization.
- Azure Virtual Desktop Architect and Technical Lead - designed multi-region AVD deployment for 500+ internal users.
- Production data migration and infrastructure modernization - 15K contract, 218 hours. Migrated 50TB+ across cloud environments with zero downtime, automated data validation reducing manual QA by 80%.
What I build:
- Production AI/ML pipelines on AWS (EKS, Lambda, SageMaker)
- Multi-agent systems and MCP server deployments on Kubernetes
- Self-hosted LLM infrastructure (Llama, open-weight models)
- ML model serving, monitoring, and inference optimization
- Terraform IaC, GitOps pipelines, CI/CD for AI workloads
- Cloud cost optimization for GPU-heavy and inference environments
How I work:
I partner with CTOs and engineering leads who need AI infrastructure that scales without breaking. No boilerplate. Every architecture decision is documented, versioned, and handed over so your team can maintain it independently.
Engagement formats:
- AI Infrastructure Audit (fixed scope, 5-day turnaround)
- Full platform build (4-12 week engagements)
- Ongoing AI/ML platform engineering (monthly retainer, async-first)
Available now. Click Invite to Job to discuss your architecture.
Steps for completing your project
After purchasing the project, send requirements so Dmitrii can start the project.
Delivery time starts when Dmitrii receives requirements from you.
Dmitrii works on your project following the steps below.
Revisions may occur after the delivery date.
Kickoff and Access (Day 1)
Align on scope and success criteria. You grant read-only IAM access. 30-minute kickoff call.
Discovery and Analysis (Days 2-3)
Analyze your AWS infrastructure across cost, reliability, security, and AI/ML workload efficiency. No changes to your environment.