Job Description

About the Role

We are looking for a Forward Deployment Engineer (FDE) to work directly with customers to design, deploy, and validate inference & reinforcement learning POCs on GMI's GPU infrastructure. This is a hybrid role spanning platform engineering, applied ML, and customer success – you'll turn research ideas into performant systems on real GPU clusters.

What You'll Do

• Own customer POCs end-to-end: deploy and optimize LLM inference, RL training, and post-training workflows
• Work hands-on with research teams, startups, and enterprise customers
• Debug performance, stability, and correctness in real environments
• Stand up and tune inference stacks (vLLM, SGLang, Ray Serve, etc.)
• Optimize latency, throughput, GPU utilization, and cost efficiency
• Support RLHF / RFT / SFT workflows using customer datasets
• Diagnose GPU, networking, and distributed system bottlenecks
• Feed customer learnings back into platform, SDKs, and APIs

What You Bring

• Strong software engineering background (Python required; Go/Rust a plus)
• Hands-on experience with ML inference or training systems
• Familiarity with distributed systems and GPUs (multi-GPU, multi-node)
• Experience with LLM inference frameworks (vLLM, SGLang, Ray Serve, Triton, etc.) – nice to have
• Experience with RL or post-training workflows (RLHF, RFT, SFT) – nice to have
• Knowledge of PyTorch, DeepSpeed, Megatron-LM, or Kubernetes-based ML platforms – nice to have
• Comfort working directly with customers and ambiguous requirements
• Ability to debug end-to-end systems (code, infra, networking, performance)
• Bilingual in English and Mandarin (required to interface with engineering teams in China)
• 2+ years of experience (no need for deep systems expertise, but strong execution mindset)
• Fast learner, strong communication and presentation skills

Why Join Us

• Work on cutting-edge inference and RL workloads – no toy demos
• Close to real users and real GPUs, not abstract roadmaps
• High ownership, fast iteration, and visible impact
• Visa sponsorship (H1B) and green card support available based on performance

Job Tags

Similar Jobs