1 year ago
Responsibilities
- Architect and optimize multi-GPU inference pipelines for large foundation-scale video models.
- Build secure, scalable cloud upload infrastructure integrating AWS S3, GCP Storage, and Azure Blob Storage with signed URLs and resumable uploads.
- Design event-driven, autoscaling distributed processing systems using Kubernetes, Pub/Sub, or Ray.
- Develop the NomadicML Python SDK, REST/gRPC APIs, and developer-facing infrastructure for video ingestion, analysis, and search.
- Build logging, tracing, and metrics pipelines for GPU utilization, job latency, and inference health.
- Support backend endpoints and TypeScript SDK bindings for web application cloud integrations and project workflows.
- Collaborate with ML researchers to productionize models and improve system reliability, performance, and usability.
Requirements
- Deep proficiency in Python, Go, or TypeScript for backend systems.
- Experience with AWS, GCP, or Azure, including IAM, object storage, and batch or compute APIs.
- Strong understanding of GPU inference scaling, Kubernetes, container orchestration, and event-driven pipelines.
- Experience designing REST or gRPC APIs, SDKs, or developer-facing infrastructure.
- Familiarity with asynchronous job orchestration tools such as Ray, Airflow, Dagster, or Temporal.
- Preferred experience with inference orchestration frameworks or ML infrastructure tools such as DeepSpeed, Triton, or Ray Serve.
- Preferred understanding of video encoding, chunking, and streaming formats for multimodal ingestion.
- Preferred basic frontend experience with React or Next.js.
- Preferred background in ML infrastructure, observability, or data management systems.
Tech Stack
Categories
About Pear VC
Pear VC is an early-stage venture capital partnership that invests at pre-seed and seed, pairing capital with hands-on support, mentorship, and programs like its PearX accelerator for founding teams. Founded in 2013 and headquartered in Menlo Park, California, it backs software and technology startups across categories. Its portfolio includes companies that reached the public markets, such as DoorDash and Guardant Health.