Lead Machine Learning Engineer, Inference & Performance

📋 Description

• Optimize Inference: Build and tune production LLM serving with vLLM and SGLang—max throughput and
• Profile & Accelerate Training: Instrument training runs; resolve bottlenecks with attention
• Engineer for the Hardware: Understand GPU architecture and attention internals; pick the right
• Serve at Scale: Deploy and operate multiple models within shared GPU clusters on GKE with
• Drive Efficiency: Own GPU utilization metrics; improve throughput-per-dollar and fleet performance.
• Collaborate & Consult: Work with clients to translate performance, latency, and cost

🎯 Requirements

• Bachelor's or Master's in CS, Engineering, or related field
• 5+ years ML/AI engineering with performance, infra, or systems focus
• Proven production deployment/optimization of models
• Experience profiling and improving GPU utilization for training or inference
• Knowledge of Data Engineering and SQL

🎁 Benefits

• Competitive salary and comprehensive benefits
• Health Insurance, Paid Leave, Holidays, Sick Leave
• Parental Leave, Bereavement Leave, 401(k) match, Employee referral bonuses
• Benefits overview: https://egen.ai/people/#benefits