Sr Software Engineer - Model Serving

Design reliable, scalable, and efficient solutions to serve models with varying latency, throughput, and computing capacity requirements. Manage the lifecycle of models, including versioning, progressive deployments, rollbacks, and updates without service interruptions. Analyze and optimize model performance and platform stability, considering response times, resource utilization, costs, and operational stability.

Experience managing, operating, troubleshooting, and basic configuration of Kubernetes and Docker Images lifecycle. Knowledge of programming or scripting for automation and operations using Python, Go, or Bash. Understanding of inference performance for machine learning models and LLMs, as well as tools for deploying machine learning models and LLMs.

Hybrid work modality. Opportunity to work on challenging and innovative projects that have a real impact on e-commerce and financial services in Latin America.