Forward Deployed Engineer (Inference & Post-Training)
AI summary of the role
Hands-on Forward Deployed Engineer acting as deep-domain specialist in inference optimization and post-training for Together AI's most strategic customers.
What you’ll do
- Optimize inference engines (vLLM, TensorRT-LLM, SGLang) for customer hardware and workloads
- Tune KV cache, speculative decoding, tensor parallelism, and quantization to hit latency/throughput targets
- Drive RL training runs and guide LoRA, SFT, DPO, RLHF, GRPO pipelines from experimentation to production
- Serve as primary technical contact for strategic accounts, ensuring optimal endpoint configuration and adoption
What you’ll bring
- 5+ years in technical role focused on inference systems, open-source LLM deployment, or post-training
- Expert-level hands-on experience with inference engines (vLLM, TensorRT-LLM, SGLang)
- Deep knowledge of KV cache tuning, speculative decoding, parallelism, and quantization
- Hands-on experience with LoRA, SFT, DPO, RLHF, GRPO pipelines
Technologies
vLLM · TensorRT-LLM · SGLang · KV cache · speculative decoding · tensor parallelism · quantization · LoRA · SFT · DPO · RLHF · GRPO
About Together AI
GPU cloud and inference platform optimized for open-source LLMs, serving 450K+ developers and enterprises with serverless APIs, dedicated clusters, and fine-tuning.
Series B
Source and classification
Implementation & delivery · Evidence for this classification:
About the role As a Forward Deployed Engineer (FDE) focused on Inference & Post-Training, you will be a hands-on technical partner to our most strategic customers — production AI teams looking to leverage high quality models and do inference at scale. For us, FDE is not a replacement for a Solutions Architect; you will partner with our SAs as a deep-domain specialist in inference optimization, fine-tuning pipelines, and production deployment. As key contributors to both the CX, Engineering, and Sales organizations, FDEs add tremendous value by ensuring we can meet the requirements of our most complex POCs, facilitate successful platform adoption, and guide tailored optimization efforts — directly impacting customer success, company growth, and the hardening of our core platform. Responsibilities Inference Engine Optimization: Select, configure, and optimize inference engine based on
More from the job description
About the role As a Forward Deployed Engineer (FDE) focused on Inference & Post-Training, you will be a hands-on technical partner to our most strategic customers — production AI teams looking to leverage high quality models and do inference at scale. For us, FDE is not a replacement for a Solutions Architect; you will partner with our SAs as a deep-domain specialist in inference optimization, fine-tuning pipelines, and production deployment. As key contributors to both the CX, Engineering, and Sales organizations, FDEs add tremendous value by ensuring we can meet the requirements of our most complex POCs, facilitate successful platform adoption, and guide tailored optimization efforts — directly impacting customer success, company growth, and the hardening of our core platform. Responsibilities Inference Engine Optimization: Select, configure, and optimize inference engine based on hardware, model architecture, and workload profile Configuration & Performance Tuning: Develop configuration updates to win critical POCs, benchmarks, and optimize customer deployments; tune KV cache, apply speculative decoding, determine optimal tensor parallelism, and determine quantization strategy to hit throughput and latency targets. Post-Training & Fine-Tuning: Drive hands-on RL training runs and optimize system design; guide customers through LoRA, SFT, DPO, RLHF, and GRPO pipelines fro [... source excerpt omitted ...] roduction. Strategic Customer Alignment: Act as the primary technical point of contact for aligned strategic accounts — monitoring and optimizing endpoint configurations, helping customers get the most out of the platform, and collaborating to ensure we hit critical milestones. Opinionated Onboarding: Establish direct alignment with strategic customers at onboarding; ensure the right inference and post-training configurations are in place from day one to improve time-to-value. Product Feedback Loop: Directly influence our software and model roadmap by surfacing insights from the field. Contribute back to the product where needed to support customer requirements or drive a bett [... source excerpt omitted ...] and GRPO; ability to advise on system design Model Landscape Awareness: Broad knowledge of state-of-the-art open-source models and strong judgment on model selection for specific customer use cases, hardware profiles, and performance targets. Coding Proficiency: Strong Python skills; comfortable working in production environments About Together AI Together AI, the AI Native Cloud, is purpose-built for AI engineers. AI application developers get high-performance inference that scales reliably, fine-tuning and reinforcement learning for creating frontier-level specialized models, and pre-training at massive scale for fully custom intelligence, all around a marketplace of leadin
Employer postings · Data from · Sources