SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Together AI is seeking a Forward Deployed Engineer (FDE) specializing in inference optimization and post-training workflows to serve as a hands-on technical partner to strategic customers. This role bridges customer success, engineering, and sales—you will work alongside Solutions Architects as a deep-domain specialist, not as a replacement.
Key responsibilities include: selecting and optimizing inference engines (vLLM, TensorRT-LLM, SGLang) based on hardware and workload profiles; tuning KV cache, speculative decoding, tensor parallelism, and quantization strategies to hit throughput and latency targets; guiding customers through fine-tuning pipelines (LoRA, SFT, DPO, RLHF, GRPO) from experimentation to production; serving as the primary technical contact for strategic accounts; establishing opinionated onboarding to ensure correct configurations from day one; and surfacing field insights to influence product and model roadmap decisions.
Required qualifications: 5+ years in a technical role with strong focus on inference systems, open-source LLM deployment, or post-training workflows. Expert-level hands-on experience with inference engines and ability to diagnose performance issues. Deep knowledge of KV cache tuning, speculative decoding, tensor parallelism, pipeline parallelism, and quantization. Hands-on experience with fine-tuning and post-training pipelines. Broad knowledge of state-of-the-art open-source models and judgment on model selection. Strong Python skills and comfort in production environments.
Must be a permanent resident or citizen of Singapore. Together AI offers competitive compensation, startup equity, health insurance, and flexibility in remote work arrangements.
About Together AI
AI / Data / Infrastructure — cloud platform for open-source and generative AI model training and inference.
