Staff AI Product Engineer
Nscale is a London-based, full-stack AI cloud and infrastructure company that provides GPU compute, managed AI services, orchestration software, data centers, and power infrastructure for AI training, fine-tuning, and inference.
Funding history
About Nscale
Nscale builds and operates vertically integrated AI infrastructure spanning software, GPU compute, networking, storage, purpose-built data centers, and power. Its active cloud platform offers self-service inference endpoints, fine-tuning, managed Kubernetes and Slurm, virtual machines, and GPU clusters.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will own architecture for model serving, reinforcement learning, post-training, and developer-facing interfaces. You will set standards for inference performance, model efficiency, fine-tuning, APIs, SDKs, and platform tooling. You will resolve cross-team architectural questions, coach engineers, and evaluate serving engines and accelerator technologies.
Requirements
- 8–12 years of engineering experience with production AI systems
- Experience setting technical direction for AI systems
- Expertise in LLM inference, caching, batching, scheduling, speculative decoding, and low-precision inference
- Hands-on expertise in RL for LLMs, including RLHF, DPO, reward modelling, or agentic RL
- Experience designing developer-facing APIs and SDKs
- Experience with control-plane and data-plane architecture
- Experience with GPU or accelerator workloads
- Knowledge of CUDA or ROCm
- Proficiency in Python and PyTorch
- Understanding of transformers and LLM production behaviour
- Experience with distributed compute and parallelism
Responsibilities
- Set technical direction for inference serving architecture
- Drive model-efficiency strategy and performance trade-offs
- Resolve systemic serving performance and reliability issues
- Own RL and post-training architecture
- Define shared inference and training infrastructure for RL loops
- Establish standards for fine-tuning services and data workflows
- Set standards for developer APIs, SDKs, tooling, versioning, and rate limiting
- Coach engineers and represent the domain in architecture reviews
Benefits
- Medical coverage
- Dental coverage
- Vision coverage
- Flexible paid time off
- Parental leave
- Retirement plan participation