资深机器学习运维工程师 (EMEA远程)
Principal ML Ops Engineer (EMEA Remote)
Location: 全远程（EMEA 时区）
Start date: 尽快开始
Languages: 需要流利的英语
Industry: 云计算 / AI / 欧洲深度科技 SaaS
关于该职位
Pragmatike 正代表一家快速扩展、资金充足的分布式云基础设施初创公司进行招聘，该公司正在构建下一代 AI 原生云服务。该公司通过去中心化架构重新定义了计算的交付方式，为 AI/ML 工作负载提供 GPU 驱动的基础设施、安全存储和高速数据传输，与传统云服务提供商相比，显著降低了环境影响。
我们正在寻找一位具有丰富经验的 ML Ops 工程师，专注于 AI 系统的生产级模型服务和基础设施。这是一个高度技术性、动手能力强的职位，专注于构建可扩展、可靠且高效的 ML 推理平台，支持实时 AI 应用。
您将负责设计和运营支撑大规模机器学习模型的服务核心基础设施。您将与基础设施、平台和应用 AI 团队紧密合作，确保高可用性、低延迟和成本高效的推理系统。强烈的所有权意识、生产导向思维以及对分布式 GPU 系统的经验是必不可少的。
您的职责
- 使用 vLLM、TGI、Triton 或等效框架构建和运营生产级模型服务基础设施
- 设计并实现具有蓝/绿和金丝雀发布策略的稳健部署流水线
- 开发和维护自动扩展系统、多模型服务架构和智能请求路由层
- 优化 GPU 利用率、内存效率、网络吞吐量和模型构件存储性能
- 设计可观测性系统，用于跟踪推理延迟、吞吐量、GPU 使用情况、成本指标和系统健康状况
- 管理模型注册表和 CI/CD 流水线，实现自动化和可重复的模型部署
- 负责 ML 系统的全生命周期，从开发到生产，包括运维支持和值班责任
- 定义工程最佳实践，并在快速发展的初创环境中为平台可扩展性做出贡献
所需的资格条件
- 在 ML Ops、平台工程、SRE 或类似聚焦于 ML 系统的基础设施岗位中，有 4 年以上经验
- 有使用 vLLM、TGI、Triton 或等效模型服务框架的实际操作经验
- 强大的背景
查看英文原文
Location: Fully remote (EMEA timezone)
Start date: ASAP
Languages: Fluent English required
Industry: Cloud Computing / AI / European Deep-Tech SaaS
ABOUT THE ROLE
Pragmatike is recruiting on behalf of a fast-scaling, well-funded distributed cloud infrastructure startup building next-generation AI-native cloud services. The company is redefining how compute is delivered by providing GPU-powered infrastructure for AI/ML workloads, secure storage, and high-speed data transfer through a decentralized architecture that significantly reduces environmental impact compared to traditional cloud providers.
We are seeking a ML Ops Engineer with strong experience in production-grade model serving and infrastructure for AI systems. This is a highly technical, hands-on role focused on building scalable, reliable, and efficient ML inference platforms powering real-time AI applications.
You will be responsible for designing and operating the core infrastructure that serves machine learning models at scale. You will work closely with infrastructure, platform, and applied AI teams to ensure high availability, low latency, and cost-efficient inference systems. Strong ownership, production mindset, and experience with distributed GPU systems are essential.
YOUR RESPONSIBILITIES
- 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
REQUIRED QUALIFICATIONS
- 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
PREFERRED QUALIFICATIONS
- Experience with ML platforms such as Kubeflow, MLflow, or KubeAI
- Knowledge of GPU scheduling, CUDA/ROCm optimization, or multi-tenant inference systems
- Experience with cost optimization across different GPU types and inference workloads
- Background in early-stage startups or greenfield infrastructure projects
- Proven experience building production systems from scratch rather than maintaining legacy platforms
WHY JOIN US
- 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.
Pragmatike is committed to a fair, transparent, and inclusive recruitment process. We do not discriminate based on age, disability, gender, gender identity or expression, marital or civil partner status, pregnancy or maternity, race, religion or belief, sex, or sexual orientation.
In accordance with GDPR, your personal data will be processed lawfully, fairly, and securely, and used solely for recruitment purposes, including sharing it with our client(s) for employment consideration.