Skip to content

About myrtle.ai

We are the world leader in low latency AI inference.

We combine deep technical expertise with future-looking vision to ensure that developers can meet their inference performance goals with our easy-to-use products.

Our mission

Machine learning algorithms make it possible to introduce AI into all walks of life, but traditional solutions often fail to deliver the performance required.

Our mission is to make low latency AI and machine learning accessible to everyone. We improve latency, throughput, energy and cost making it possible to effortlessly deploy the machine learning models companies need to ensure their growth.

Our story

Founded in 2017 by UK-based PhDs, we work with partners and customers across the world. With deep industry roots, we are a team of hardware/software co-design specialists, infrastructure experts and machine learning scientists you can rely on.

Why myrtle.ai?

We are the trusted partner that enables machine learning developers to meet their inference performance goals, no matter the scale, complexity or industry.

Lowest latency inference

Run machine learning inference
in microseconds

Trusted AI partner

Free engineers to advance development

Frictionless deployment

Iterate and deploy effortlessly, no matter your scale

World-leading low latency AI inference

Discover how our low latency AI inference products can increase machine learning performance across industries

Make smarter trading decisions faster with microsecond AI inference
Learn more

Our impact

We increase the performance of machine learning inference workloads for edge applications and applications in cloud or enterprise data centers. Our products ensure all available compute resources achieve the lowest deterministic latency and fastest throughput.

Up to
20x 
Lower latency than competitors
Trading
10x 
Lower CapEx
and OpEx
Speech
10x 
More compute density per server
Recommendation

Our team

Meet our expert team

Peter is the founder of Myrtle.ai, which has focused on hardware-software co-design for efficient machine learning inference and other core data-center workloads since 2017. Through Peter, Myrtle.ai was instrumental in setting up the speech transcription benchmark for MLPerf. Peter previously founded a software development company which wrote distributed data center software. He was also a Senior Technical Director at several multinational visual effects companies. Peter holds a PhD in Pure Mathematics from Cambridge University, UK.

Tom was previously Executive Vice President of Sales and Marketing at Marvell Technology. Prior to joining Marvell in 2016, Tom spent 12 years at Broadcom in a variety of executive leadership roles, including EVP of Business Development, EVP of Worldwide Sales, and SVP and General Manager of the Enterprise Computing Group. Tom earned an M.S. in Electrical Engineering from the University of Southern California and a B.S. in Electrical Engineering from Ohio State University.

Giles has global experience in design, sales and marketing roles with ASIC, FPGA and IP companies. Since 2018 he has focused on FPGA acceleration for machine learning applications and he joined Myrtle.ai in 2019.

Careers

What our clients say

"We are very happy with VOLLO. We prefer that our competition doesn't know we use it."
Anonymous

Increase the performance of your machine learning models

Discover how myrtle.ai can help you access low latency inference and deploy complex machine learning models that run in microseconds