Modal is hiring a Senior Senior ML Platform Engineer on the Serverless ML team (Hybrid · New York, United States). This is a hands-on role in LLM & generative AI—not a generic “AI enthusiast” post.
You will own LLM features, retrieval, agents, and evaluation end to end: problem framing, offline evaluation, safe rollout, and iteration from production signals. Success is measured with clear metrics (quality, latency, cost, or business KPIs)—not slide decks alone.
Modal provides serverless GPU infrastructure for AI teams. Platform engineers make it trivial to run training, batch jobs, and inference at scale.
Senior ML Platform Engineer (NYC): schedulers, cold-start optimisation, and developer experience for Python-first ML workflows.
Hybrid NYC — equity and generous GPU credits for personal projects.
What you will do
- Improve container scheduling, autoscaling, and GPU utilisation.
- Build SDK ergonomics for LangChain, PyTorch, and batch inference.
- Partner with customers running large fine-tuning and eval workloads.
- Own reliability SLOs for multi-tenant GPU clusters.
Stack & environment
- Python, Kubernetes, AWS, Docker.
- Hybrid Madison Avenue NYC.
What we look for
- ML platform or infra engineering with GPU workloads.
- Strong Python and systems debugging.
- US work authorization.