🛠 Tech Stack

💼 About This Role

You'll own the infrastructure that brings AI models to life in production, from optimizing LLM inference to deploying real-time voice AI agents. You will sit at the intersection of ML and infrastructure, designing systems that power real-time computer vision and conversational AI at scale.

🎯 What You'll Do

• Design and maintain inference infrastructure for AI products
• Own end-to-end deployment pipeline for AI models
• Architect and scale Kubernetes clusters for GPU workloads
• Build infrastructure for real-time AI agents and WebRTC
• Drive inference scaling strategies like speculative decoding

📋 Requirements

• 5+ years in infrastructure engineering, 2+ years focused on AI/ML workloads
• Strong experience with Kubernetes for GPU-accelerated workloads
• Hands-on experience with model serving and inference optimization
• Solid understanding of LLM inference optimization techniques
• Experience with Infrastructure as Code (Terraform) and GitOps

✨ Nice to Have

• Experience with LLM serving engines like vLLM or SGLang
• Experience with NVIDIA Triton and TensorRT
• Familiarity with WebRTC infrastructure and real-time media streaming

🎁 Benefits & Perks

• 🏖️ Unlimited vacation
• 💻 Remote or Hybrid work policy
• 🏥 Health and well-being program (digital therapist sessions)
• 📈 Career development and growth with competitive salary
• 🚀 Fast-paced environment with high-tech startup