Jobiglo

No results.

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

Together AI · Singapore

New
Senior 🇬🇧 English
vLLM TensorRT-LLM SGLang LoRA SFT DPO RLHF GRPO Python

Job description

About the role

Together AI is hiring a Forward Deployed Engineer (FDE) focused on Inference and Post-Training in Singapore. The FDE is a hands-on technical partner to production AI teams that want to run high-quality models at scale, working alongside Solutions Architects as a deep-domain specialist in inference optimization, fine-tuning pipelines and production deployment. The role sits at the intersection of customer experience, engineering and sales, and supports complex POCs, platform adoption and tailored optimization.

Candidates must be a permanent resident or citizen of Singapore.

Key responsibilities

  • Inference engine optimization: select, configure and optimize the inference engine according to hardware, model architecture and workload profile.
  • Configuration and performance tuning: develop configuration updates to win POCs and benchmarks, tune KV cache, apply speculative decoding, set optimal tensor parallelism and choose a quantization strategy to hit throughput and latency targets.
  • Post-training and fine-tuning: run RL training runs, optimize system design, and guide customers through LoRA, SFT, DPO, RLHF and GRPO pipelines from experimentation to production.
  • Strategic customer alignment: act as the primary technical contact for aligned strategic accounts, monitor and optimize endpoint configurations and help customers get the most out of the platform.
  • Onboarding: establish direct alignment with strategic customers at onboarding so the right inference and post-training configurations are in place from day one.
  • Product feedback loop: surface field insights to influence the software and model roadmap, contribute back to the product where needed, and drive early adoption of features and research with strategic customers.

Required profile

  • 5+ years in a technical role, with a strong focus on inference systems, open-source LLM deployment or post-training workflows.
  • Expert-level, hands-on experience with inference engines such as vLLM, TensorRT-LLM and SGLang, able to diagnose and resolve performance issues at the engine level.
  • Broad knowledge of state-of-the-art open-source models and sound judgment on model selection for customer use cases, hardware profiles and performance targets.
  • Strong Mandarin speaking ability.

Required skills

  • Deep knowledge of KV cache tuning, speculative decoding, tensor and pipeline parallelism, and quantization techniques.
  • Hands-on experience with LoRA, SFT, DPO, RLHF and GRPO pipelines.
  • Strong Python skills and comfort working in production environments.

What we offer

  • Competitive compensation, startup equity, health insurance and other benefits.
  • Flexibility in terms of remote work.

Questions fréquentes

Le salaire n'est pas communiqué publiquement par le recruteur. Vous pouvez postuler et négocier directement avec Together AI.
Cliquez sur "Postuler maintenant" en haut de la page. Vous pouvez importer votre CV en 1 clic — Jobiglo extrait automatiquement vos informations et postule pour vous.

Why are you reporting this job?

Thank you for your report. We will review this job.

Explore further

Salaries, guides and searches in Singapore.

Apply in 30 seconds

Enter your email to apply. An account will be created automatically.

Apply now →

By continuing, you accept our terms of use.

Already have an account? Login

A question about this job?

Ask it here: you will get the full job summary by e-mail, right away.

Published 18 hours ago

Expires 1 month from now

9 views · 0 interested

Boost your chances

Upload your CV — we will match you with relevant openings.

Analyzing your CV...

Together AI

Singapore