Forward Deployed Engineer - Mandarin Speaking

Deploys and optimizes inference and post-training systems for strategic customers, including engine tuning, fine-tuning pipelines, and production adoption. Requires 5+ years of technical experience, expert inference-engine knowledge, strong Python skills, and Singapore citizenship or permanent residency.

About the job

Responsibilities

Select, configure, and optimize inference engines based on hardware, model architecture, and workload profiles.
Develop configuration updates for critical POCs and benchmarks, and optimize customer deployments.
Tune KV cache, apply speculative decoding, determine optimal tensor and pipeline parallelism, and select quantization strategies to meet throughput and latency targets.
Drive hands-on RL training runs and optimize system designs.
Guide customers through LoRA, SFT, DPO, RLHF, and GRPO pipelines from experimentation through production.
Serve as the primary technical point of contact for strategic accounts.
Monitor and optimize endpoint configurations and collaborate with customers to achieve critical milestones.
Establish direct technical alignment during onboarding and ensure appropriate inference and post-training configurations are in place.
Surface field insights to influence software and model roadmaps.
Contribute product improvements to support customer requirements and drive feature and research adoption.

Requirements

5+ years of experience in a technical role focused on inference systems, open-source LLM deployment, or post-training workflows.
Expert-level, hands-on experience with inference engines such as vLLM, TensorRT-LLM, or SGLang.
Ability to diagnose and resolve performance issues at the inference-engine level.
Deep knowledge of KV cache tuning, speculative decoding, tensor parallelism, pipeline parallelism, and quantization techniques.
Hands-on experience with fine-tuning and post-training pipelines, including LoRA, SFT, DPO, RLHF, and GRPO.
Ability to advise on post-training system design.
Broad knowledge of state-of-the-art open-source models and sound judgment in model selection for customer use cases, hardware profiles, and performance targets.
Strong Python skills and comfort working in production environments.
Must be a permanent resident or citizen of Singapore.

Compensation & Benefits

Competitive compensation
Startup equity
Health insurance
Other benefits
Flexibility in terms of remote work

Salary ranges are determined by location, level, and role. Individual compensation is based on experience, skills, and job-related knowledge.

Skills

Python, vLLM, Tensorrt-Llm, Sglang, Kv Cache, Speculative Decoding, Tensor Parallelism, Pipeline Parallelism, Quantization, Lora, Sft, Dpo, RLHF, Grpo, Open-Source Llms