Forward Deployed Engineer – Inference, Post-Training, Mandarin Speaking

Together AI

. Select, configure, and optimize inference engines based on hardware, model architecture, and workload profile .

Posted 11/3/2026full-timeRemote • SingaporeMid-LevelSeniorWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates expertise in optimizing inference engines and post-training workflows, with a strong focus on KV cache tuning, tensor parallelism, and customer engagement. Proven ability to drive technical solutions and enhance customer deployments through hands-on experience with state-of-the-art open-source models.

Highest-signal resume keywords

Inference Engine OptimizationKV Cache TuningPost-Training WorkflowsPython ProgrammingCustomer Engagement

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

Inference SystemsOpen-Source LLM DeploymentPerformance Issue DiagnosisQuantization TechniquesFine-Tuning PipelinesSpeculative DecodingTensor ParallelismPipeline ParallelismLoRASFT

Soft Skills

Strong JudgmentCollaborationCustomer Guidance

Tools & Technologies

VLLMTensorRT-LLMSGLang

Industry Keywords

Production EnvironmentsModel SelectionPerformance TargetsCustomer ExperienceStrategic Accounts

Tech Stack

Tools & technologies

Python

About the role

Key responsibilities & impact

Select, configure, and optimize inference engines based on hardware, model architecture, and workload profile
Develop configuration updates to win critical POCs and benchmarks and optimize customer deployments
Tune KV cache, apply speculative decoding, determine optimal tensor and pipeline parallelism, and determine quantization strategies to meet throughput and latency targets
Drive hands-on RL training runs and optimize system design
Guide customers through LoRA, SFT, DPO, RLHF, and GRPO pipelines from experimentation through production
Act as the primary technical point of contact for strategic accounts
Monitor and optimize endpoint configurations and help customers maximize platform value
Collaborate with customers to achieve critical milestones
Establish direct alignment with strategic customers during onboarding
Ensure appropriate inference and post-training configurations are in place from day one
Surface field insights to influence the software and model roadmap
Contribute to the product to support customer requirements and improve the customer experience
Drive early feature and research adoption with strategic customers

Requirements

What you’ll need

Must be a permanent resident or citizen of Singapore
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, or SGLang
Ability to diagnose and resolve performance issues at the 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 system design
Broad knowledge of state-of-the-art open-source models
Strong judgment on model selection for specific customer use cases, hardware profiles, and performance targets
Strong Python skills
Comfortable working in production environments

Benefits

Comp & perks

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