Software Optimization Compiler Engineer, Mythic
Redwood City, CA
Chip manufacturer for AI applications
Job no longer available
Chip manufacturer for AI applications
101-200 employees
Job no longer available
Redwood City, CA
101-200 employees
Company mission
Mythic's mission is pushing the limits of AI performance and capability.
Role
Who you are
- Knowledgeable in C++ (C++14 or newer)
- Strong Python programming skills
- 2+ years of experience and background in design and development in compiler optimization, mathematical optimization, or combinatorial optimization domains
- Develop technical specifications and break them down into tasks and phases
- Create project roadmaps with delivery timelines
- Prototype new ideas and improve the existing code base
- You are a self-starter and are comfortable with a high level of independence and discretion to complete your work
Desirable
- You have a background in research record and interest in systems programming and machine learning
- You have knowledge of modern back-end stack
- Some contributions to open-source infrastructure such as TensorFlow, Pytorch, ONNX, etc
- Experience retargeting LLVM, GCC, or compiler infrastructure, Use of clang, OpenCL , or other in-house compiler
What the job involves
- Build custom compiler that compiles and optimizes deep-neural-network definitions for our hardware
- Design and build optimization strategies for efficient use of Mythic hardware to meet the performance target such as latency, throughput, power etc
- Work with hardware designers on architecture optimizations
- Work with data scientists on training neural networks optimized for Mythic hardware
- Compiling, transforming and optimizing neural networks to custom hardware architectures
- Build tools to collect and analyze performance bottlenecks
- Developing tools and feedback mechanisms to improve neural network training and inference
- Creating sophisticated simulations that provide deep insight on hardware performance and optimizations
Our take
Mythic is a startup making artificial intelligence chips for use in gadgets such as smart home devices or security cameras. The enthusiasm for chip startups is a result of a need by companies using AI software. Silicon Valley venture capitalists are responding by pouring money into the semiconductor industry, enticed by a new generation of AI chips like Mythics to challenge industry giants Intel and Nvidia.
To avoid the book sized chips which burn 100 watts and cost $4000, Mythic uses analog circuits rather than digital to create its processor, with easier memory integration and device operation and using 10 times less power. Driving costs and production times down and making their product an attractive choice for companies using AI software.
With a recent $70million funding round Mythic can begin the mass production of their chips and development of the next generation of hardware and software products.
Kirsty
Company Specialist at Welcome to the Jungle
Insights
14% employee growth in 12 months
Company
Funding (last 2 of 7 rounds)
May 2021
$70m
SERIES C
Jun 2019
$30m
SERIES B
Total funding: $152.5m
Company benefits
- $150 quarterly wellness benefit
- HSA/FSA: Mythic contributes $1000 for single and $2750 for family per year if you enroll in high deductible plan
- $3400 annual education benefit for conferences, classes or purchase of books
- Commuter: Caltrain & MetroRail passes; scooter, bike, public transit and parking stipend
- Work from home opportunities
- Health insurance
Company HQ
Redwood Shores, Redwood City, CA
Leadership
Dave Fick
(CTO)Earned a PhD in Computer Science and Engineering from the University of Michigan. Previously Graduate Student Research Assistant at the University of Michigan for 5 years.
Mike Henry
(CEO)Earned a BSc, an MSc, and a PhD in Electrical and Computer Engineering from Virginia Tech.
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