Pragmatike logo
Pragmatike

Remote first tech projects

AI Infrastructure Engineer – GPU

Infrastructure EngineerInfrastructure EngineerFull TimeRemoteSeniorTeam 11-50Since 2022H1B No SponsorCompany SiteLinkedIn

Location

Ukraine

Posted

37 days ago

Salary

0

Seniority

Senior

Bachelor Degree4 yrs expEnglishDistributed SystemsPythonTerraform

Job Description

AI Infrastructure Engineer – GPU

Pragmatike

• Build and operate production-grade model serving infrastructure using frameworks such as vLLM, TGI, Triton, or equivalent • Design and implement robust deployment pipelines with blue/green and canary rollout strategies for ML models • Develop and maintain auto-scaling systems, multi-model serving architectures, and intelligent request routing layers • Optimize GPU utilization, memory efficiency, network throughput, and model artifact storage performance • Design observability systems for tracking inference latency, throughput, GPU usage, cost metrics, and system health • Manage model registries and CI/CD pipelines enabling automated and reproducible model deployments • Own the full lifecycle of ML systems from development through production, including operational support and on-call responsibilities • Define engineering best practices and contribute to platform scalability in a fast-moving startup environment

Job Requirements

  • 4+ years of experience in ML Ops, Platform Engineering, SRE, or similar infrastructure roles focused on ML systems
  • Hands-on experience with model serving frameworks such as vLLM, TGI, Triton, or equivalent
  • Strong background in container orchestration and operating GPU-based workloads in production
  • Experience with MLOps tooling including model registries, experiment tracking, and automated deployment pipelines
  • Proficiency in Python and infrastructure-as-code tools (e.g., Terraform, Helm, or similar)
  • Strong understanding of distributed systems, performance tuning, and production reliability engineering
  • Ability to effectively use AI coding assistants to accelerate development and debugging workflows
  • Ownership mindset with the ability to operate independently in a remote-first environment
  • Experience with ML platforms such as Kubeflow, MLflow, or KubeAI (preferred)
  • Knowledge of GPU scheduling, CUDA/ROCm optimization, or multi-tenant inference systems (preferred)
  • Experience with cost optimization across different GPU types and inference workloads (preferred)
  • Background in early-stage startups or greenfield infrastructure projects (preferred)
  • Proven experience building production systems from scratch rather than maintaining legacy platforms (preferred).

Benefits

  • Take ownership of critical infrastructure powering a rapidly scaling AI-native cloud platform
  • Build foundational ML inference systems from the ground up in a high-growth, well-funded startup
  • Work at the intersection of distributed systems, GPU computing, and sustainable cloud architecture
  • Gain deep expertise in next-generation AI infrastructure and large-scale model serving systems
  • Influence core engineering decisions and define best practices that will scale with the company.

Related Categories

Related Job Pages

More Infrastructure Engineer Jobs

Launch Legends logo

Cofounder - Head of Legal (Digital Assets & Financial Infrastructure) for Exciting Blockchain Project

Launch Legends

Launch Legends is a worldwide team of renegade artists, scientists, & engineers who bring back insights from the future.

Full TimeRemoteTeam 51-200Since 2021H1B No Sponsor

Shape the Future of Blockchain—Bringing Business On-Chain We’re offering a unique opportunity to join Launch Legends (and Autheo) as a part-time Equity Cofounder . Founded nearly four years ago, Launch Legends is at the forefront of bridging Web3 blockchain technology with the next evolution of Web2 integration—bringing businesses on-chain through enterprise-grade solutions, DePIN innovations, and decentralized financial infrastructure. Our flagship project, Autheo , is an AI enabled Layer-Zero OS with an integrated Layer-1 blockchain and complete decentralized infrastructure that includes decentralized compute, storage, identity, and service marketplaces, as well as a Full-stack development environment (DevHub)—engineered for scalable enterprise adoption, developer innovation, and real-world blockchain integration. Autheo is building a next-generation financial infrastructure platform that integrates ISO 20022 messaging, banking rails, and digital asset systems into a unified architecture. This is a rare opportunity to join as a cofounder and help define the legal, regulatory, and financial foundation of a new category of institution. Our Projects - Autheo – www.autheo.com - Autheo Team - https://www.autheo.com/teams - Launch Legends (Parent Company) – www.launchlegends.io - Twitter : https://x.com/Autheo_Network About Autheo With nearly 100 equity cofounders from leading companies and institutions—many with advanced degrees and PhDs—Autheo is solving the critical challenges blocking business adoption of blockchain technology. Key Features: - Enterprise-Grade Layer-1 Blockchain – High-speed, self-securing, and cost-efficient infrastructure built for scale. - Developer Hub & Application Marketplace – A decentralized platform where developers build, deploy, and monetize real-world apps. - Web2-Web3 Integration – Microservices, SDKs, and governance frameworks for seamless business migration. - Decentralized Cloud & Compute – Secure, privacy-preserving storage and AI-powered compute for next-gen applications. - DePIN Infrastructure – On-chain networks powering real-world infrastructure ownership and resource sharing. Traction (Testnet Launch): - Wallet Accounts: 290,000+ - Twitter Followers: 30,000+ - Discord Members: 19,000+ - Smart Contracts Deployed: 30,000+ - Developers Registered for MVP DevHub: 7,500+ Compensation & Growth Path This is a part time equity / token-based cofounder opportunity. You will receive equity in Launch Legends , Autheo , and the WFO Creator Network , along with token allocations in the Autheo blockchain. We have already completed an initial financing round to support infrastructure and marketing, and are currently in discussions with VCs and crypto investors to fund expansion and salaries. Salaried compensation is expected to begin within 4 to 5 months, following our node, token sales or funding. ROLE: Cofounder — Head of Legal (Digital Assets & Financial Infrastructure) As a part-time Cofounder — Head of Legal (Digital Assets & Financial Infrastructure) in an equity-based cofounder role, you will lead all legal strategy across digital assets, payments, and financial infrastructure as we build toward a regulated banking framework. Key Responsibilities: 1. Legal Strategy Leadership - Lead comprehensive legal strategy for blockchain, payments, digital asset custody, and platform operations. - Structure compliant legal frameworks for integrated banking and digital asset services. 2. OCC & Regulatory Support - Provide direct legal support for the OCC charter application in coordination with banking strategy. - Draft and oversee core legal documentation, policies, agreements, and compliance programs. 3. Cross-Functional Collaboration - Work closely with product, compliance, engineering, and executive leadership to embed legal considerations into platform design and operations. Qualifications: Required: - Significant experience in fintech, digital assets, payments, or financial services law. - Strong understanding of regulatory bodies including OCC, SEC, CFTC, and FinCEN. - Ability to operate effectively in a fast-moving, early-stage environment. Preferred: - Prior in-house legal leadership at a fintech, crypto, or regulated financial institution. - Experience supporting bank charter or trust company applications. Soft Skills: - Strategic legal thinker who balances innovation with regulatory compliance. - Collaborative leader with strong communication across technical and business teams. Deliverables (90 Days): - Comprehensive legal roadmap covering digital assets, payments, and OCC charter requirements. - Initial set of core legal templates, policies, and agreements for platform operations. - Legal gap analysis and support materials for OCC application. - Cross-functional legal training and embedding of compliance-by-design principles. - Risk assessment of key legal exposures in integrated banking + blockchain model. 🌐 🚀 WHY JOIN LAUNCH LEGENDS? - Traction with Momentum : Autheo is already gaining significant traction in the blockchain space, with rapid developer adoption, platform growth, and partnership interest. - Cross-Industry Impact ; Autheo is positioned to transform not only the Web3 ecosystem—but also Web2 and the broader technology sector—by enabling real-world business adoption of decentralized infrastructure. - Real Innovation, Not Hype : Unlike many blockchain ventures, Autheo is focused on substance over speculation. We are building real solutions: modular fullstack infrastructure, enterprise-grade toolkits, decentralized identity, cloud, compute, and service orchestration. - Backed by Elite Talent : You’ll join a team composed of professionals from top-tier universities, Fortune 500 companies, and major blockchain platforms. Our team includes multiple PhDs and senior engineers who have launched and scaled world-class technologies. If you're ready to redefine blockchain adoption , empower global business integration , and help shape the next generation of Web3 and developer ecosystems , we invite you to take the next step. Let’s build the future—together.

United States
Qualitest Group logo

Azure Cloud Infra Engineer

Qualitest Group

Qualitest Group is a global engineering company whose services and expertise are powered by artificial intelligence. Qualitest Group helps businesses reach their goals and prioriti

Role Description We are looking for an experienced DevOps Engineer with strong expertise in Azure Cloud and Infrastructure Automation using Terraform. The ideal candidate will have hands-on experience in CI/CD pipeline setup using Jenkins, solid scripting skills, and a good understanding of cloud security and networking concepts within Azure. Qualifications - Strong experience and understanding of Azure resources and services; good exposure to AKS (Azure Kubernetes Service). - Hands-on experience in Infrastructure as Code (IaC) using Terraform for automated environment provisioning and management. - Proficient in Bash or Shell scripting for automation and deployment tasks. - Experience in creating and managing CI/CD pipelines for infrastructure deployment. Requirements - Knowledge of cloud security audits and Azure networking concepts. - Experience in troubleshooting Jenkins issues related to infrastructure deployments. Company Description

India
Leidos logo

Senior Cloud Cybersecurity Infrastructure Engineer

Leidos

Leidos is an innovation company rapidly addressing the world’s most vexing challenges in national security and health.

Full TimeRemoteTeam 10,001+Since 1969H1B Sponsor

• Help manage underlying infrastructure for a cloud-based Next-generation Continuous Integration/Continuous Deployment (CI/CD) pipeline. • Work in a peer-to-peer environment placing a high value on collaboration and team success. • Implementation, maintenance, and troubleshooting of a complex and diverse cloud environment. • Providing Subject Matter Expertise for cloud Information Assurance on various implementations. • Securing high-availability systems via industry/DOD standards and best practices. • Configuring & securing Azure/AWS cloud resources for build, release & deployment pipelines. • Supporting an enterprise CI/CD environment with multiple servers, operating systems and applications. • Building and maintaining scripts for automation of tasks and server maintenance.

California
$107.9K - $195.1K / year
Job Closed
Iterable logo

Senior Infrastructure Engineer

Iterable

Headquartered in San Francisco, California, Iterable is a privately held internet company offering a growth marketing platform that enables marketers to automat

• Use your Kubernetes and AWS expertise to evolve EKS lifecycle, multi-tenant isolation, and regional consistency, ensuring clusters remain secure, performant, and predictable as we scale • Improve reliability and cost by identifying areas of waste (storage, compute) • Improve automation of our Elasticsearch cluster management system (shard management, data retention, indexing, cross cluster re-balancing)

United States
$133.5K - $212K / year