Staff Machine Learning Engineer
Cars
Apr 2025 - Sep 2025 (6 months)
Started the ML and Data Platform practice at CARS24, grown to a lean team of 6 members. We are also responsible to optimize costs, which has been reduced by more than 60% in the last 4 years (for existing services and small incremental costs for new services/integrations/data growth).
. Migrated DS workloads (40+ realtime APIs) to GKE to enable better scaling, reduced
latency and management of deployments (rollouts, canary deployment, monitoring, alerts)
. Worked with Data Scientists to optimize their code and model for better throughput
. Deployed 45+ DL models (MaskRCNN, PaddleOCR, ResNet, EfficientNet, Stable Diffusion with UNet) using Triton Inference Server for multi-model serving, saving GPU cost by ~5x
. Depl