5 months ago
Responsibilities
- Build and operate an end-to-end ML platform covering training, evaluation, deployment, and monitoring.
- Create scalable training workflows with orchestration, infrastructure, resource management, model packaging, registries, dataset lineage, experiment tracking, checkpointing, and deployment automation.
- Build reliable inference deployments and model delivery pipelines with versioning, reproducibility, rollback, approval gates, evaluation gates, and production observability.
- Design and operate GPU allocation, scheduling, utilization, benchmarking, and resource-efficiency systems across training and inference workloads.
- Establish production SLOs for latency, availability, error rate, GPU saturation, cold-start time, inference cost, and model quality drift.
- Standardize inference serving infrastructure and optimize batching, quantization, CUDA graphs, memory-aware scheduling, throughput, latency, reliability, and cost.
- Partner with research teams to productionize new multimodal and generative AI capabilities and drive execution across teams.
Requirements
- 10+ years of software engineering or infrastructure experience, including 5+ years in ML infrastructure, MLOps, distributed systems, or AI platform engineering.
- Deep experience with Python, PyTorch, Kubernetes, Docker, cloud infrastructure, and GPU-based workloads.
- Strong understanding of distributed systems and large-scale ML infrastructure design.
- Experience with ML workflow orchestration systems such as Ray, Kubeflow, Argo, Airflow, Flyte, or Metaflow.
- Experience deploying and managing production inference systems using Triton, vLLM, TensorRT-LLM, Ray Serve, KServe, Seldon, BentoML, TorchServe, or custom services.
- Experience with model registries, experiment tracking, CI/CD for ML, canary deployments, shadow traffic, rollback strategies, and production monitoring.
- Strong cloud experience across AWS, GCP, Azure, CoreWeave, Lambda Labs, or RunPod.
- Ability to debug performance bottlenecks across distributed systems, containers, networking, GPU memory, and storage layers.
- Ability to define architecture, establish platform standards, and drive execution across teams.
- Preferred: experience with multimodal, vision, generative AI, large-scale GPU clusters, A100/H100, NCCL, high-throughput data pipelines, generative AI evaluation and monitoring, ML security, privacy, data governance, or internal developer platforms.
Benefits
- Build core AI infrastructure that directly shapes the deployment, monitoring, scalability, performance, and cost efficiency of real-world AI products.
- Own critical infrastructure decisions end-to-end and work on high-leverage GPU efficiency and large-scale deployment problems.
- Work in a high-velocity, low-bureaucracy environment with close collaboration across research, platform, and product teams.
- Help accelerate AI capabilities into partner-facing fashion and e-commerce experiences.
Tech Stack
Categories
About SpreeAI
SpreeAI builds AI-powered virtual try-on, sizing, and styling tools for fashion retailers and brands, delivered through web and mobile integrations and a partner portal. The company sells SaaS and SDKs that embed photorealistic try-on into ecommerce sites, in-store displays, and clienteling apps to reduce returns and improve conversion. Founded in 2023 and headquartered in Los Angeles, it integrates with platforms like Shopify to onboard brand partners quickly.