Forward Deployed Engineer (Inference & Post-Training) - Mandarin Speaking

📋 Description

• Hands-on technical partner to strategic customers
• Focus on inference, post-training, and optimization
• Collaborate with SAs on POCs and deployments
• Drive time-to-value with onboarding and configurations
• Influence product roadmap from field insights

🎯 Requirements

• 5+ years in a technical role
• Expert with inference engines (e.g., vLLM, TensorRT-LLM)
• Deep KV cache, decoding, parallelism, quantization expertise
• Post-training experience: LoRA, SFT, DPO, RLHF, GRPO
• Strong Python in production settings
• Open-source model awareness for customer use cases

🎁 Benefits

• Competitive compensation and startup equity
• Health insurance and other benefits
• Flexibility in remote work