Principal Performance Engineer – Lead

🕒 Abril 7

🍂 Massachusetts – Remoto

🍂 Massachusetts – Remote

💵 $169.300 - $304.700 / ano

⏰ Tempo Integral

🟠 Sênior

👷🏻‍♀️ Engenheiro

🦅 Patrocina Visto H1B

Esta empresa já patrocinou vistos H1B no passado.

Candidatar-se

Encontrar Vagas Remotas Similares

Receber Emails de Vagas Remotas

📊 Verifique sua pontuação de currículo para esta vaga

Melhore suas chances de conseguir uma entrevista verificando sua pontuação de currículo antes de se candidatar.

Enviar Currículo

Akamai Technologies

SiteLinkedInTodas as Vagas

5001 - 10000 funcionários

🔒 Cibersegurança

💰 Post-IPO Equity em 2001-07

Cloud Computing • Cybersecurity • Content Delivery

A Akamai Technologies é um provedor líder de serviços em nuvem especializado em oferecer soluções de segurança, computação em nuvem e entrega de conteúdo. A empresa oferece uma gama de serviços, como segurança de API, proteção contra DDoS e otimização de desempenho para aplicativos web, garantindo experiências de usuário seguras e confiáveis. Com uma infraestrutura global robusta, a Akamai capacita empresas a otimizar sua presença digital, protegendo contra diversas ameaças cibernéticas e melhorando o desempenho de aplicativos.

Descrição

• Optimize inference performance across the Akamai Inference Cloud • Collaborate closely with hardware performance engineers to deliver end-to-end optimization • Apply and evaluate quantization, distillation, and pruning techniques to optimize model performance while preserving accuracy • Design hardware-aware model placement and scheduling strategies to match models with optimal compute resources • Implement and tune speculative decoding, KV-cache optimization, and batching strategies to improve inference throughput and latency • Build benchmarking and profiling pipelines to measure model-layer performance across architectures, hardware, and serving configurations • Mentor and guide engineers on the team through code reviews, design discussions, and technical problem-solving • Collaborate with hardware performance engineers to identify and resolve end-to-end performance bottlenecks across the inference stack

🎯 Requisitos

• 12+ years of relevant experience with a Bachelor's or Master's degree in Computer Science, Machine Learning, or a related field • Possess hands-on experience optimizing LLM inference performance (quantization, speculative decoding, model compression, etc.) • Have a solid understanding of transformer architectures and how design choices impact latency, throughput, and accuracy • Possess experience with inference serving frameworks such as vLLM, TensorRT-LLM, Triton, or similar systems • Be proficient in Python and C++ with experience profiling and optimizing compute-intensive workloads • Have familiarity with hardware-aware optimization, including GPU/accelerator scheduling and memory management trade-offs

🏖️ Benefícios

• healthcare • 401K savings plan • company holidays • vacation (in the form of PTO) • sick time • family friendly benefits including parental leave • employee assistance program including a focus on mental and financial wellness