.png){kind=logo}
Intel is seeking an AI Frameworks Engineer to develop PyTorch, TensorFlow, and JAX for enterprise-level AI production in a variety of environments due to the technical nature of LLMs (language model behavior).
This position will focus on improving the speed and quality of training and inference, creating high-performance Machine Learning (ML) Kernel solutions, improving debugging capabilities for the complex systems involved in AI, integrating with community-based open-source solutions, and providing production-ready AI capabilities within various enterprise environments at Intel.
Location: Bangalore, India
Job Type: Full-time
Job ID: JR0277797
Apply: Click Here
Design and develop various software features in AI frameworks, such as PyTorch device plugins and ML kernels.
Improve deep learning training and inference capabilities in the AI software stack at Intel.
Identify and apply optimization opportunities to enhance the performance of deep learning workloads.
Contribute to the open-source community by enabling Intel GPUs and upstreaming code.
Debug complex problems in multi-tiered software systems; ensure integration across frameworks.
Work on frameworks and platforms deployed to production environments.
Apply HW-SW optimization techniques and contribute to high-performance AI solutions.
Minimum qualifications for this position include:
Bachelor's or Master’s Degree (or equivalent) in Computer Science/Electrical Engineering or related technologies (Computer systems, Digital circuits etc).
6 to12 years professional experience in Artificial Intelligence frameworks and GPU (Graphics Processor Unit) programming.
Strong skills in C++ with intermediate programming skills with Python and GPU programming experience.
Experience developing Machine Learning kernels (GEMM (Generalised Matrix Multiplication)), Convolution, Flash Attention, Mixture of Experts).
Use of Artificial Intelligence Frameworks such as PyTorch, Tensorflow, JAX.
Knowledge of Natural Language Processing (NLP) and Large Language Model (LLM) Deep Learning Models.
Strong understanding of computer system architectures, Hardware-Software (HW-SW) Integration, Optimisation Knowledge.
Strong verbal and written communication skills; ability to collaborate effectively in a global cross-geography team environment.
Experience developing CUDA (Compute Unified Device Architecture) and Triton-based kernels.
Familiarity with compiler algorithms for heterogeneous systems and fusion optimisations.
Intel Corporation (Intel) is a leading global technology company focused on leading the world in developing innovative solutions through Semiconductor Technology and the x86 microprocessor for the world’s computing devices. Intel has built upon its technology roots, being one of the original Semiconductor companies, and continues today to drive technological advancements in computing, Artificial Intelligence (AI), Networking, and other new and emerging technologies and deliver them to consumers, businesses, and enterprises through a wide variety of industries.
