🛠 Tech Stack

💼 About This Role

You'll join the Kimchi team to optimize LLM inference performance, focusing on throughput, latency, and KV cache efficiency for a growing customer base. You'll lead the technical direction of inference optimization with high autonomy. This role directly impacts customer p99 latency and company margins.

🎯 What You'll Do

• Push throughput via continuous batching and kernel-level tuning
• Cut latency by profiling and fixing bottlenecks
• Optimize KV cache utilization with paged attention and prefix caching
• Quantize weights and activations without quality regression

📋 Requirements

• 5+ years building production ML systems
• Strong Python skills with production services experience
• Hands-on experience with vLLM, SGLang, or TensorRT-LLM
• Fluency in quantization tradeoffs and measurement

✨ Nice to Have

• Distributed systems experience with collective communication
• Knowledge of multi-GPU and multi-node inference
• Self-direction in a wide mandate role

🎁 Benefits & Perks

• 💰 Competitive salary plus equity options
• 🏖️ Flexible remote-first global environment
• 📚 Learning budget for conferences and courses
• 💻 Equipment budget for your home office
• 🗓️ Extra days off for work-life balance

📨 Hiring Process

Estimated timeline: 3-5 weeks

1. 1Screening call with Recruiter· 30 min
2. 2Hiring Manager interview· 45 min
3. 3Technical interview (system design)· 60 min
4. 4Live coding· 60 min
5. 5Culture Check interview with executive· 45 min