Software Engineer, Neural Magic

vLLM, GPU

Salary not provided

+ Stock Options

C++

CUDA

Junior, Mid and Senior level

Boston

Office located in Somerville, MA

Simplifying machine intelligence

Open for applications

Simplifying machine intelligence

21-100 employees

B2BArtificial IntelligenceEnterpriseDeep TechMachine LearningSaaS

Open for applications

Salary not provided

+ Stock Options

C++

CUDA

Junior, Mid and Senior level

Boston

Office located in Somerville, MA

21-100 employees

B2BArtificial IntelligenceEnterpriseDeep TechMachine LearningSaaS

Company mission

To reduce the cost and increase the performance of end-users deploying deep learning applications.

Job

Company

Role

Who you are

Extensive experience in writing high performance code for GPUs and deep knowledge of GPU hardware
BS, MS, or PhD in computer science or computer engineering
CUDA
High performance computing
Mathematical software, especially linear algebra or signal processing
Modern C++
Tensor computations
Deep neural network models and techniques
A self-directed practitioner who learns fast
Strong communications skills with both technical and non-technical team members
Strong sense of project ownership and personal responsibility
Genuine interest in learning

What the job involves

As a Software Engineer focused in vLLM, you will be at the forefront of innovation, collaborating with our team to tackle the most pressing challenges in model performance and efficiency
Your work with machine learning and high performance computing will directly impact the development of our cutting-edge software platform, helping to shape the future of AI deployment and utilization
Write robust and modern C++ and CUDA, working on high-performance machine learning primitives, performance analysis and modeling, and numerical methods
Review code and help develop best practices for the team
Work closely with machine learning teams to attain high performance for neural networks in vLLM

Our take

The edge AI market has expanded exponentially, but hardware solutions like GPUs can result in added costs due to the complexities they introduce into hardware and software infrastructures. Neural Magic has developed an interface engine that runs at GPU speeds but is compatible with already running computer CPUs, reducing costs while speeding up processes.

Since the company’s launch in 2019, new startups including NeuReality, Deci, and Deep Cube have emerged. While these startups offer some sort of edge AI software, the scope of Neural Magic’s optimized models provides leading support for data scientists, engineers, and developers.

Funding secured will help advance operations and further Neural Magic's business reach. As the first company to offer free open-source modelling in an expanding and lucrative market, the company is well positioned to be a leading force in machine learning acceleration.

Steph

Company Specialist at Welcome to the Jungle

Company

Funding (last 2 of 3 rounds)

Oct 2021

$30m

SERIES A

Nov 2019

$15m

SEED

Total funding: $50m

Company benefits

Medical/Dental/Vision Insurance
401(k) & IRA
Paid Time Off (Vacation, Sick & Public Holidays)
Family Leave
Short Term & Long Term Disability
Training & Development
Work From Home
Free Food and Snacks
Wellness Resources
Stock Option Plan

Company HQ

Davis Square, Somerville, MA

Articles

Neural Magic Raises $30M in Series A Funding

Neural Magic, Which Offers Software for Growing Edge AI Market, Gets $30M Boost

Future is Sparse: Prof Nir Shavit, Neural Magic

Revolutionizing Machine Learning: Striveworks & Neural Magic Partner to Offer High-Performance CPUs

Leadership

Alex Matveev

(CTO)

Former Research Scientist and Postdoctoral Associate at MIT. Received their PhD in Computer Science from Tel Aviv University.

Salary benchmarks

We don't have enough data yet to provide salary benchmarks for this role.

Submit your salary to help other candidates with crowdsourced salary estimates.

Share this job

View 2 more jobs at Neural Magic