Member of Technical Staff, Inference

About the Company

Mirendil is a tech-first company focused on solving core bottlenecks that unlock step-change acceleration across science and technology. We are building a frontier AI research company and training our own models end-to-end, with a team including researchers and engineers from Anthropic, Google DeepMind, xAI, OpenAI, Microsoft, Apple, and MIT.

Responsibilities

• Design and build high-throughput, low-latency inference serving systems for frontier models
• Optimize inference performance across GPU and accelerator hardware to maximize FLOPs utilization and memory bandwidth
• Enable and extend distributed inference frameworks like vLLM, SGLang, or TensorRT-LLM
• Implement and validate inference-time optimizations including speculative decoding, quantization, and KV cache management
• Build observability and reliability infrastructure to measure latency, throughput, and cost
• Partner with teams to bring new model architectures and post-training techniques into production

Requirements

• Experience owning inference systems in production or research environments
• Proficiency across the full inference stack from serving infrastructure to hardware-level optimization
• Experience with large-scale model deployment and distributed inference frameworks