Yevhenii H. looks like a good fit?
We can organize an interview with Aldin or any of our 25,000 available candidates within 48 hours. How would you like to proceed?
Schedule Interview NowYevhenii H. - Devops, Amazon ECS for Kubernetes, Git
My name is Yevhenii H. and I have over 6 years years of experience in the tech industry. I specialize in the following technologies: Python, Amazon Web Services, DevOps, CI/CD, DevOps Engineering, etc.. I hold a degree in . Some of the notable projects I’ve worked on include: Migration of RAG Platforms from On-Premise to Cloud Kubernetes, GPU Cost Optimization with Spot + Reserved Instance Combinations, ML Training & Deployment Pipelines, Migration of AI Services from On-Premise to Cloud, AI/ML Migration & GPU Scaling with K8s – AWS, GCP, Azure, etc.. I am based in Kiev, Ukraine. I've successfully completed 16 projects while developing at Softaims.
I approach every technical challenge with a mindset geared toward engineering excellence and robust solution architecture. I thrive on translating complex business requirements into elegant, efficient, and maintainable outputs. My expertise lies in diagnosing and optimizing system performance, ensuring that the deliverables are fast, reliable, and future-proof.
The core of my work involves adopting best practices and a disciplined methodology, focusing on meticulous planning and thorough verification. I believe that sustainable solution development requires discipline and a deep commitment to quality from inception to deployment. At Softaims, I leverage these skills daily to build resilient systems that stand the test of time.
I am dedicated to making a tangible difference in client success. I prioritize clear communication and transparency throughout the development lifecycle to ensure every deliverable exceeds expectations.
Main technologies
Devops
6 years
Python
5 Years
Amazon Web Services
5 Years
DevOps
1 Year
Additional skills
Direct hire
Potentially possible
Experience Highlights
Migration of RAG Platforms from On-Premise to Cloud Kubernetes
Led migration of RAG systems, LLMs, AI NLP pipelines, computer vision, AI chatbots, AI video, and ML model training from on-premise to cloud-native Kubernetes (AWS EKS, GCP GKE, Azure AKS). Implemented blue/green deployments, containerized ML/NLP/Computer Vision models with Docker & Helm, GPU/TPU autoscaling, and MLOps pipelines. Achieved zero downtime, 40% faster AI/NLP inference, 30% GPU cost reduction, and enhanced scalability, reliability, and efficiency of enterprise AI/ML workflows.
GPU Cost Optimization with Spot + Reserved Instance Combinations
Designed and delivered a GPU cost optimization solution for AI/ML training and inference workloads, leveraging a hybrid model of Spot GPU instances and Reserved GPU instances. Implemented Kubernetes GPU autoscaling, multi-region GPU utilization, and FinOps reporting dashboards to track performance and cost efficiency. Achieved 65% GPU cost savings, maintained SLA reliability for critical AI services, and enabled scalable, flexible cloud GPU infrastructure for long-term cost efficiency.
ML Training & Deployment Pipelines | MLflow, DVC, TensorFlow, PyTorch
Implemented automated ML training and deployment pipelines using GitHub Actions, GitLab CI, and ArgoCD for LLMs, RAG systems, NLP, and computer vision models. Integrated MLflow and DVC for experiment tracking, version control, and reproducibility. Containerized models with Docker, deployed on Kubernetes, and served via Triton Inference Server. Optimized TensorFlow, PyTorch, and vLLM workflows, achieving zero downtime, 3x faster model releases, scalable inference, and streamlined MLOps for enterprise AI/ML teams.
Migration of AI Services from On-Premise to Cloud | AWS, GCP, Azure
Migrated on-premise AI/ML inference services to AWS, GCP, and Azure, implementing ML pipelines, MLOps, model tuning, AI NLP, computer vision Python, GPT-3 NLP, TensorFlow, PyTorch, and AI model training. Designed cloud architectures and blue/green deployments for zero downtime. Achieved 28% GPU cost reduction, 35% latency improvement, and optimized workflows for data scientists, AI developers, ML engineers, and cloud solution architects.
AI/ML Migration & GPU Scaling with K8s – AWS, GCP, Azure | ML Engineer
Led migration of ai ml & machine learning python services from on-prem to AWS, GCP, Azure. Cloud architectures with GPU scaling on NVIDIA for ai chatbot, ai video, ai midjourney, nlp machine learning, gpt-3 nlp & llms, ml ops pipelines for ml model training, ai model training, model tuning, ML workflows, model deployments with PyTorch, TensorFlow, TensorFlow Lite & Hugging Face. By ml engineer, azure data engineer, have open ai & RAG systems integrations, optimized computer vision opencv, deep learning computer vision, & 3d computer vision pipelines with ai solution deployment at scale.
Education
National Technical University of Ukraine 'Kyiv Polytechnic Institute'
in Telecomunication
2010-01-01-2016-01-01
Languages
- English
- Russian
- Ukrainian
Stackoverflow