🛠 Tech Stack

💼 About This Role

You'll build and operate the systems that turn raw compute into useful intelligence — the inference services that serve LLMs at scale and the data pipelines that feed them. One week you're hunting a tail-latency regression; the next you're redesigning a Ray pipeline for petabyte scale. You'll partner directly with researchers and ML engineers to make experimental workloads run reliably in production.

🎯 What You'll Do

• Design and operate distributed inference systems for LLMs.
• Build large-scale data pipelines with Ray Data or Spark.
• Debug production failure modes and improve observability.
• Partner with researchers to productionize experimental workloads.

📋 Requirements

• 5+ years building distributed systems in production.
• Experience with Ray, Spark, or similar large-scale framework.
• Strong fluency in Python and a systems language (Go, Rust, C++).
• Knowledge of GPU/accelerator stack (CUDA, NCCL, mixed precision).
• Experience with Kubernetes and operating production incidents.

✨ Nice to Have

• Hands-on with LLM inference engines (vLLM, SGLang, etc.).
• Experience with lakehouse formats (Iceberg, Delta, Hudi).
• Open-source contributions to relevant projects.

🎁 Benefits & Perks

• 🌍 Annual travel stipend to explore a new country.
• 🍽️ Weekly lunch stipend for take-out or groceries.
• 🏥 Comprehensive medical benefits.
• 🏖️ Generous paid time off.
• 🤝 Flexible hybrid work with in-person collaboration in Bay Area.

📨 Hiring Process

Estimated timeline: 2-4 weeks · AI estimate

1. 1Recruiter Screen· 30 min
2. 2Technical Interview· 60 min
3. 3System Design Interview· 60 min
4. 4Hiring Manager· 45 min
5. 5Offer· 15 min