Job TitleLLM Infrastructure EngineerLocationRemote - US Time Zones (EST- PST)Job TypeFull-timeRole OverviewWe are seeking an LLM Infrastructure Engineer with hands-on experience building the systems that power large language models.
This is a full-time, hands-on engineering role focused on designing, deploying, and scaling the infrastructure behind model training, fine-tuning, and inference.
You will work closely with machine learning and engineering teams to make sure models run reliably, efficiently, and cost-effectively in production.
The adecuado candidate understands both the demands of LLM workloads and the cloud systems needed to support them at scale.Key ResponsibilitiesDesign, build, and maintain infrastructure for training, fine-tuning, and serving large language modelsDeploy and scale LLM inference services with a focus on latency, throughput, and reliabilityManage GPU compute resources and optimize workload scheduling and utilizationBuild and maintain data pipelines that support model training and evaluationImplement monitoring, logging, and alerting for model performance and system healthOptimize infrastructure costs while maintaining performance and availabilityAutomate deployment workflows using infrastructure-as-code and CI/CD practicesCollaborate with ML engineers and researchers to move models from experimentation into productionProactively identify bottlenecks, investigate root causes,



and resolve infrastructure issuesRequired QualificationsProven experience building large language model infrastructure (non-negotiable)Hands-on experience deploying and serving machine learning models in production environmentsStrong programming skills in Python, with experience in systems or backend developmentExperience with containerization and orchestration tools such as Docker and KubernetesSolid understanding of distributed systems, GPU computing, and performance optimizationStrong written and spoken English with a clear, professional communication styleMust have prior remote work experience, be fluent with remote collaboration tools and platforms (such as Slack, Zoom, Google Workspace, Asana, or similar), and have ideally worked with US or UK-based companiesApplications without this experience will not be consideredPreferred QualificationsStrong AWS experience, including services such as EC2, EKS, S3, and SageMakerPrior experience working at a large company or within enterprise-scale engineering environmentsFamiliarity with LLM serving frameworks such as vLLM, TensorRT-LLM, or Triton Inference ServerExperience with infrastructure-as-code tools such as Terraform or CloudFormationExperience with distributed training frameworks such as PyTorch Distributed, DeepSpeed, or RayTools & TechnologyAWSPythonDocker and KubernetesTerraform or CloudFormationPyTorch and LLM serving frameworksCI/CD and monitoring toolsSlack, Zoom, and other remote collaboration tools
#J--Ljbffr

📌 Llm Infrastructure Engineer (Santa Fe)
🏢 Hire Hangar
📍 Santa Fe