LLM Infrastructure Engineer

This is a fully remote position, open to applicants in Argentina.

📋 Description

• Design, develop, and sustain infrastructure for the training, fine-tuning, and deployment of large language models.

• Implement and scale LLM inference services to enhance latency, throughput, and reliability.

• Oversee GPU compute resources while optimizing workload scheduling and utilization.

• Construct and maintain data pipelines for both model training and evaluation purposes.

• Establish monitoring, logging, and alerting systems to track model performance and system health.

• Optimize infrastructure costs while ensuring performance and availability are upheld.

• Automate deployment processes utilizing infrastructure-as-code and CI/CD methodologies.

• Work collaboratively with ML engineers and researchers to transition models from experimentation to production.

• Identify performance bottlenecks, investigate root causes, and resolve infrastructure-related issues.

⛳️ Requirements

• Demonstrable experience in building infrastructure for large language models (a must).

• Practical experience in deploying and serving machine learning models within production settings.

• Proficient programming skills in Python, particularly in systems or backend development.

• Familiarity with Docker and Kubernetes technologies.

• Strong understanding of distributed systems, GPU computing, and performance optimization techniques.

• Excellent written and verbal communication skills in English, maintaining a clear and professional style.

• Previous experience working remotely.

• Proficiency with remote collaboration tools and platforms such as Slack, Zoom, Google Workspace, Asana, or similar applications.

• Ideally, experience working with companies based in the US or UK.

• Extensive experience with AWS services, including EC2, EKS, S3, and SageMaker.

• Background in large organizations or enterprise-scale engineering environments.

• Knowledge of vLLM, TensorRT-LLM, or Triton Inference Server.

• Experience with Terraform or CloudFormation for infrastructure management.

• Familiarity with PyTorch Distributed, DeepSpeed, or Ray frameworks.

🏝️ Benefits

• Highly competitive and transparent compensation structure.

• Attractive, market-leading salary.

• Long-term career development opportunities.

• Opportunities for personal and professional growth.