Applications are invited from interested candidates for Deep Learning Deployment Engineer (Edge AI) at CONXAI, Bengaluru, Karnataka.
About CONXAI
The $12 Trillion construction industry is one of the “least digitalized” industries and has a major productivity problem. We aim to empower the construction industry with No-Code AI to revolutionize knowledge management and help close the productivity gap.
Job Description
We are building the first NO-CODE AI PLATFORM for the AEC industry, with the 3rd generation Explainable AI, that allows users to create complex use cases with zero coding at the frontend and neuro-symbolic AI under the hood.
Key Responsibilities
We are looking for a Deep Learning Deployment Engineer (Edge AI) to join our Bengaluru office.
You will be part of our product development team and will work closely with other AI Engineers to optimize and deploy AI models on the edge hardware at scale.
- Optimize AI Models (compression, quantization, etc) on the Edge hardware such as NVIDIA Jetson, Adreno etc.
- Deploy the optimized AI Models and tailor it for specific Edge hardware
- Lifecycle management of the deployed models
- The technology will scale in public/private cloud across a rapidly increasing number of customers in multiple geographies, while processing and rendering large amounts of image based data points.
Requirements
- B Tech / M Tech in Computer Engineering from a top tier university
- 5+ years of hands-on experience with Machine Learning & Deep Learning models and their deployment to production on Edge devices
- Exceptional programming skills with C/C++ and Python
- Demonstrable experiences in deployment and optimisation of AI systems on the Cloud, Server and Edge Hardware
- Experience with computer architecture, low-level optimisation, via compilers or manual.
- Good understanding of Deep Learning Frameworks and workloads
- Experience in SoC or/and GPU acceleration for AI
- Experience in embedded systems, and real time EDGE OS development
- Experience in automation strategies for deployment of deep learning models
- Experience in Parallel Computing Platforms/General-purpose computing on graphics such as CUDA, OPENCL
- Experience in periphiral communication protocols like SPI, UART, CAN, I2C, etc.
- Experience in at least one of the wireless communication protocols like Bluetooth, Wifi, LoraWAN, etc.
- Experience in AI model optimization techniques (compression, quantization, etc)
- Excellent communication skills in English
How to Apply?
Interested candidates can apply for the post through this link.
