Senior ML Embedded Engineer

Senior ML Embedded Engineer

Location:
Ramat Hahayal, Tel Aviv

Employment Type:
Full-time

Company:
GSI Technology – A publicly traded, international high-tech company (NASDAQ: GSIT) developing the cutting-edge Gemini Associative Processing Unit (APU) for computer-in-memory acceleration.

GSI is pioneering the Gemini APU—a cutting-edge, game-changing processor designed to accelerate compute-intensive tasks like large language models, machine learning, advanced image processing, and radar imaging.

If you're passionate about architecting high-performance software systems, implementing advanced algorithms, and drilling into low-level technical details, this is the role for you.

We're seeking a dynamic and fast-learning engineer with a passion for diving deep into large language model implementations, and a keen focus on performance optimization and efficient execution.

Position Overview

We are seeking a highly skilled and motivated
Senior ML Embedded Software Engineer
to lead the development and optimization of AI models — including
Large Language Models (LLMs)
and
Vision Language Models (VLM;s)
— on GSI's proprietary APU. This role bridges high-level machine learning understanding with low-level system and performance engineering, primarily in
Python
,
C and C++
. You will be responsible for architecting, implementing, and optimizing AI pipelines under hardware constraints, with a strong emphasis on
computer vision
and
transformer architectures
.

Key Responsibilities

• Develop and optimize software libraries for CNNs, LLM's and VLM implementations on embedded hardware.
• Design end-to-end system flows integrating AI models, especially in computer vision domains.
• Lead performance tuning efforts under constraints such as memory, compute, and latency.
• Work closely with hardware teams to co-design software optimized for GSI's APU.
• Debug and optimize AI inference pipelines, including Python-based pre/post-processing where applicable.
• Team up across disciplines to turn wild ideas into reliable, high-performance code.
• Architect and develop a high-performance AI compiler framework for deploying quantized neural networks on the GSI Gemini edge platform, enabling advanced edge AI workloads and optimizing for low-latency inference, efficient hardware utilization, and seamless integration with hardware acceleration pipelines.

Required Qualifications

• B.Sc. in Computer Science or Electrical Engineering from a leading university.
• 5+ years of experience in embedded software development using
  C++ and C
  .
• Solid experience in one or more of the following:
  Computer Vision
  ,
  RT-Embedded
  ,
  DSP
  .
• Proven experience in developing and optimizing
  AI pipelines
  under
  performance, memory, and latency constraints
  .
• Proven track record in
  performance/memory-constrained programming
  .
• Strong communication skills, analytical mindset, and attention to detail.
• Independent, solution-oriented, and highly motivated to make things happen
• Proven track record developing and optimizing software algorithms with deep consideration for hardware architecture, memory bandwidth, and system constraints
• Strong understanding of processor architecture fundamentals—caches, pipeline stages, execution units, and memory hierarchies
• Ability to interpret detailed hardware specifications and translate them into robust, efficient software solution.

Preferred Qualifications

• Practical experience with
  transformer architectures
  and/or
  vision-language models (VLMs)
  .
• Deep knowledge of computer vision pipelines and multimodal systems.
• Experience designing complex software systems from concept to deployment.
• Familiarity with
  hardware-aware optimization techniques
  such as:
• Quantization
• Pruning
• Kernel fusion
• Experience with
  performance profiling tools
  (e.g., PyTorch Profiler, NVIDIA Nsight).
• Low-level optimization experience with
  CUDA
  ,
  OpenCL
  , or
  hardware-specific SDKs
  .

Privacy Statement

All applications will be handled with strict confidentiality. Your information will not be shared without your consent.