AI Infrastructure Engineer - AI, Data & Platforms

📋 Description

• Design and operate training, fine-tuning, and inference infra.
• Build pipelines for LLMs and ML models across batch, real-time, and streaming.
• Optimize inference across accelerators (GPU/TPU) and fine-tuning workflows.
• Stand up evaluation, monitoring, alerting, and rollback for prod models.
• Partner with AI Eng to remove infra friction and speed deployment.
• Establish best practices for model versioning, artifacts, reproducibility, and responsible AI in finance.

🎯 Requirements

• 6+ years in ML infrastructure, MLOps, or platform engineering with AI focus.
• Strong Python; model serving frameworks (vLLM, Triton, Ray, TorchServe).
• Hands-on production deployment and fine-tuning of models.
• Cloud fundamentals across AWS, GCP, or Azure; containers and Kubernetes.
• Inference optimization across accelerators; quantization and autoscaling.
• Pragmatic, production-focused engineering; collaboration with teams.

🎁 Benefits

• 4-day in-office with 1-day flexible work arrangement.
• Equal opportunity employer; inclusive culture.
• Reasonable accommodations provided on request.