Research Engineer - Inference

Overview

Research Engineer focused on deploying and optimizing frontier AI models in production, turning research breakthroughs into real-time products.

What you'll do

• Deploy state-of-the-art models to production and own the path from research to serving infrastructure.
• Optimize inference performance across the stack for latency, throughput, and cost.
• Use techniques such as quantization, distillation, KV-cache optimization, batching strategies, and custom kernels.
• Build and tune high-performance serving systems for real-time, streaming workloads.
• Create tooling and infrastructure for researchers to ship new models safely and quickly.

What you'll need

• Experience deploying and serving ML models in production, ideally for latency-sensitive or real-time applications.
• Strong GPU programming and inference optimization skills (e.g., CUDA, Triton, TensorRT, or vLLM/SGLang).
• Ability to autonomously profile and eliminate bottlenecks across the serving stack.
• No requirement for formal certifications or degrees.
• Ability to demonstrate hard problem-solving via artifacts like past projects/designs or GitHub contributions.

Details

• Remote role executable globally; optional work from offices in London, New York, San Francisco, and Warsaw.