Senior Inference Optimization Engineer — Remote, Equity

FDE Times; Singapore; Remote; SGD 140,000 - 200,000; Full time

Benefits offered by this job

Startup equity

Health insurance

Remote-friendly

Job summary

Together AI is seeking a Forward Deployed Engineer focused on Inference & Post-Training to partner with strategic customers for production AI deployments at scale. You will optimize inference pipelines, tune configurations, and guide customers from experimentation through production.

You will collaborate with SAs and engineering teams, applying LoRA, SFT, DPO, RLHF, and GRPO techniques while helping shape the product roadmap through field insights and early feature adoption.

Qualifications

• 5+ years in a technical role focused on inference systems.
• Expert-level experience with inference engines (e.g., vLLM, TensorRT-LLM, SGLang).
• Deep knowledge of KV cache tuning, speculative decoding, tensor parallelism, and quantization techniques.
• Hands-on experience with fine-tuning and post-training pipelines (LoRA, SFT, DPO, RLHF, GRPO).
• Strong Python skills and production deployment capabilities.

Responsibilities

• Optimize inference engines based on hardware, model architecture, and workload profile.
• Develop configuration updates to win critical POCs, benchmarks, and optimize deployments; tune KV cache, speculative decoding, tensor parallelism, and quantization strategies.
• Drive hands-on RL training runs and guide customers through LoRA, SFT, DPO, RLHF, and GRPO pipelines from experimentation through production.
• Act as the primary technical contact for aligned strategic accounts, guiding endpoint configurations and ensuring value from the platform.
• Establish onboarding alignment with strategic customers to ensure correct inference and post-training configurations from day one.
• Influence product roadmap by surfacing field insights and driving early feature adoption with strategic logos.

Skills

Python

Inference optimization

Post-training workflows

Production environments

Open-source LLM deployment

Tools

vLLM

TensorRT-LLM

SGLang

Job description

Together AI is seeking a Forward Deployed Engineer focused on Inference & Post-Training to partner with strategic customers for production AI deployments at scale. You will optimize inference pipelines, tune configurations, and guide customers from experimentation through production.

You will collaborate with SAs and engineering teams, applying LoRA, SFT, DPO, RLHF, and GRPO techniques while helping shape the product roadmap through field insights and early feature adoption.