Job Description

Do you thrive on optimizing AI systems for peak performance?

Are you ready to push the boundaries of inference speed & efficiency - and set the standard for how it's done?

Join the Akamai Inference Cloud Team!

The Akamai Inference Cloud team is part of Akamai's Cloud Technology Group. We build AI platforms for efficient, compliant, and high-performing applications. These platforms support customers in running inference models and empower developers to create advanced AI solutions effectively. #AIC

Partner with the best

The Senior Performance Engineer oversees benchmarking, optimization strategies, and performance of the AI inference platform. Responsibilities include applying advanced techniques to enhance throughput, reduce latency, and improve resource utilization globally. This role involves working with models, hardware, and infrastructure while mentoring engineers. Decision-making, influencing architecture, and establishing performance standards are key to delivering exceptional results at scale.

As a Senior Performance Engineer, you will be responsible for:

• Leading benchmarking and profiling of AI models and inference workloads across different hardware configurations, measuring latency.
• Researching and implementing model optimization techniques including quantization, pruning, distillation, and hardware-specific optimizations.
• Optimizing and refining inference frameworks and infrastructure to enhance performance, collaborating with TensorRT, vLLM, TorchServe, Triton, and related platforms.
• Owning the performance baselines and regression monitoring strategy for the platform, and driving resolution of systemic and complex performance issues.
• Leading technical efforts across engineering teams, resolving inefficiencies, designing optimization strategies, verifying enhancements, and guiding engineers in performance-focused approaches.
  
  

Do What You Love

To be successful in this role you will:

• Have very good experience in performance engineering with hands-on expertise in AI/ML model optimization and inference performance tuning.
• Apply expertise in inference optimization techniques like quantization, model compilation, hardware acceleration, and ML compilers to achieve measurable production improvements.
• Show proficiency with GPU optimization and understanding of memory hierarchies and techniques to maximize hardware utilization.
• Have experience with profiling and benchmarking tools for AI workloads, identifying performance bottlenecks in distributed systems.
• Exhibit effective communication abilities, aligning engineering, product, and infrastructure teams to shape and guide technical direction.
• Demonstrate problem-solving skills with ability to analyze performance data.
• Possess knowledge of distributed inference and model parallelism techniques.
• Have experience with cost optimization for compute-intensive workloads.
  
  

Work in a way that works for you

FlexBase, Akamai's Global Flexible Working Program, is based on the principles that are helping us create the best workplace in the world. When our colleagues said that flexible working was important to them, we listened. We also know flexible working is important to many of the incredible people considering joining Akamai. FlexBase, gives 95% of employees the choice to work from their home, their office, or both (in the country advertised). This permanent workplace flexibility program is consistent and fair globally, to help us find incredible talent, virtually anywhere. We are happy to discuss working options for this role and encourage you to speak with your recruiter in more detail when you apply.

Learn what makes Akamai a great place to work

Connect with us on social and see what life at Akamai is like!

We power and protect life online, by solving the toughest challenges, together.

At Akamai, we're curious, innovative, collaborative and tenacious. We celebrate diversity of thought and we hold an unwavering belief that we can make a meaningful difference. Our teams use their global perspectives to put customers at the forefront of everything they do, so if you are people-centric, you'll thrive here.

Working for you