Embedded AI Software Engineer

We are looking for a Embedded AI SW Engineer to design and deploy AIenabled embedded systems around a multivendor AI chiplet this role you will bridge hardware lowlevel AI accelerators and complex software stacks to enable sustainable safety and securityaware AI pipelines in embedded automotive or industrial environments. 

Key responsibilities:

• Execute embedded deployment of neural network models including model slicing retraining (or finetuning) strategies and quantizationaware deployment. 
• Deployment and tuning of AI models on embedded targets including memory bandwidth and poweraware partitioning. 
• Integrate selected AI accelerator toolchains into the internal tool environment enabling endtoend model development optimization and deployment. 
• Extend and evolve AI Glue (OpenVX gluecode generator) to automate mapping of AI graphs and kernels to heterogeneous chiplets and backends. 
• Integrate and visualize AI pipeline behavior and performance via PRISMbased or similar visualization tools. 
• Develop and optimize OpenVX accelerator backends and kernels for the Bosch chiplet project including computer vision pipelines and different AI workloads. 
• Implement and tune OpenCL and Vulkan kernels for sensor and image processing pipelines (image acquisition and pre-processing) on GPU and hardware accelerators. 
• Collaborate with hardware teams to define and refine chipletspecific APIs memory models and communication protocols (e.g. UCIe hostside drivers). 
• Ensure sensortoAI data flows are optimized for bandwidth latency and determinism including safetycritical constraints where applicable. 

Qualifications :

• Strong proficiency in C and embedded systems programming with experience in realtime or safetycritical environments. 
• Expertise in OpenVX OpenCL and/or GPU compute frameworks (e.g. Vulkan) especially for computer vision and/or AI pipelines. 
• Good understanding of AI chiplets heterogeneous acceleration and highspeed interconnects (e.g. UCIe) and hostside drivers. 
• Experience with AI model deployment on embedded targets including model partitioning slicing quantization and toolchain integration (e.g. TensorRT ONNXRuntime vendorspecific stacks). 
• Familiarity with AI accelerator toolchains and neural network models to AI chiplet mapping. 
• Knowledge of OpenVX gluecode generators / AI glue frameworks and experience in extending such code generators is a strong plus. 
• Understanding of safety- and securitycritical requirements (e.g. ISO 26262 AUTOSAR or industrial safety standards) and how to monitor AI workloads in such environments. 
• Good written and verbal communication skills with the ability to document architecture APIs and integration guidelines. 

Additional Information :

LikeABosch Benefits:

Your work-life balance is valuable to us so we offer you:

• 25 Days of annual leave because work-life balance is essential to us;   
• Flexible working hours and if you want to work from somewhere else than the office our Home Office program helps you do that 70% of your working time/month.

Your health and well-being is important to us so we have you covered:

• Medical subscription;
• Accident insurance;
• Sport activities and well-being initiatives.

We believe in a Life-Long Learning approach so you can take advantage of:

• Technical and soft skills trainings;
• Access to e-learning platforms;
• Local and Global career development programs;
• Opportunity to attend conferences;
• Bookster subscription.

You will be part of a product company. You will contribute to developing end-to-end products that are delivered to Global OEMs.

On top of these we are offering:

• A monthly budget which can be used for several different services on an online benefit platform;
• Annual bonus;
• Lunch discounts.

Ready to work LikeABosch

We live by our values have an open feedback culture and there is plenty of room for innovative ideas. All because a team is only as valuable as its members.

Remote Work :

No

Employment Type :

Full-time