Forward Deployed Engineer (Inference & Post-Training)

Join our team as a Forward Deployed Engineer (FDE) focused on Inference & Post-Training. In this role, you will be a hands-on technical partner to our most strategic customers, helping them leverage high-quality models and do inference at scale. You will work closely with our Solutions Architects as a deep-domain specialist in inference optimization, fine-tuning pipelines, and production deployment. Your contributions will directly impact customer success, company growth, and the hardening of our core platform.

• Act as a hands-on technical partner to strategic customers, focusing on inference optimization, fine-tuning pipelines, and production deployment.
• Select, configure, and optimize inference engines based on hardware, model architecture, and workload profile; develop configuration updates to win critical POCs.
• Drive hands-on RL training runs and optimize system design; guide customers through LoRA, SFT, DPO, RLHF, and GRPO pipelines from experimentation through production.

• Post-Training Knowledge: Hands-on experience with fine-tuning and post-training pipelines, including LoRA, SFT, DPO, RLHF, and GRPO; ability to advise on system design
• Inference Optimization: Deep knowledge of KV cache tuning, speculative decoding, tensor parallelism, pipeline parallelism, and quantization techniques
• Coding Proficiency: Strong Python skills; comfortable working in production environments
• Inference Engine Depth: Expert-level, hands-on experience with inference engines (e.g., vLLM, TensorRT-LLM, SGLang); ability to diagnose and resolve performance issues at the engine level
• 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
• Experience: 5+ years in a technical role, with a strong focus on inference systems, open-source LLM deployment, or post-training workflows