Job Details:

Job Description: 

Our Team is dedicated to research and development for the future of AI - unprecedented scale for enabling machine intelligence on Edge, desktop, and mobile computers. While achieving a minimal power consumption and tremendous computing power, Intel AI accelerators are targeting daily use for millions of devices. Join the adventure of harnessing the complexity of state-of-art Deep Neural Networks and most advanced AI hardware accelerators in the word. The Neural Network Compiler Optimization team is looking for a highly motivated Software Engineer with a graph theory background and problem-solving skills.

Our team is working to utilize the OpenVINO toolkit and underlying MLIR infrastructure in order to redefine the limits of Neural Networks performance for the Visual Processing Units generations to come. The successful candidate will be part of our efforts to research and develop graph-based compilation algorithms for broad horizontal scaling for the new Neural Network back-end compiler project and will be cooperating on a daily basis with runtime software, research, infrastructure and front-end teams.

Responsibilities:

• Driving design for a compilation flow that will scale to future Neural Network architectures and target platforms.
• Implementing compilation passes for enabling and optimizing Neural Networks workloads.
• Development of performance analysis, visualization, and profiling tools.
• Integrating and testing changes, owning the tasks execution end-to-end.
• Contributing into compilation features roadmap planning.

Qualifications:

Minimal Qualifications:

• BS/MS in Computer Science or a similar field.
• At least 3-4 years of experience in programming.
• Excellent C++ programming skills.
• Strong production software engineering background, experience with CI, code reviews, paired programming, unit and integration testing.
• Proven track of experience in contributing in large-scale, multi-component software systems.

Preferred Qualifications:

• Experience in one the following: compiler technologies, computer vision, numerical modelling, high-performance computing, deep-learning frameworks or algorithms.
• Experience in development of graph-based algorithms, e.g. production solutions based on graph coloring, maximum cut, shortest path, etc.
• Experience in AI hardware accelerators, GPU, heterogeneous architectures software development.
• Experience in mapping between Neural Networks architectures and hardware accelerated inference.
• Experience in LLVM/MLIR.
• Python programming skills.

Job Type:

Experienced Hire

Shift:

Shift 1 (Romania)

Primary Location: 

Romania, Timisoara

Additional Locations:

Business group:

The Software Team drives customer value by enabling differentiated experiences through leadership AI technologies and foundational software stacks, products, and services. The group is responsible for developing the holistic strategy for client and data center software in collaboration with OSVs, ISVs, developers, partners and OEMs. The group delivers specialized NPU IP to enable the AI PC and GPU IP to support all of Intel's market segments. The group also has HW and SW engineering experts responsible for delivering IP, SOCs, runtimes, and platforms to support the CPU and GPU/accelerator roadmap, inclusive of integrated and discrete graphics.

Posting Statement:

All qualified applicants will receive consideration for employment without regard to race, color, religion, religious creed, sex, national origin, ancestry, age, physical or mental disability, medical condition, genetic information, military and veteran status, marital status, pregnancy, gender, gender expression, gender identity, sexual orientation, or any other characteristic protected by local law, regulation, or ordinance.

Position of Trust

N/A

Work Model for this Role

This role will be eligible for our hybrid work model which allows employees to split their time between working on-site at their assigned Intel site and off-site. * Job posting details (such as work model, location or time type) are subject to change.