Principal Software Engineer

Syntiant Corp.; India; On-site; INR 9,532,888 - 14,299,332; Full time

Job summary

Syntiant Corp., located in India, is seeking a Principal Software Engineer to lead the development of model converter code for edge AI applications. The role requires over 8 years of experience in ML for edge devices, strong proficiency in C/C++ and Python, and experience with ML frameworks such as TensorFlow and PyTorch. This opportunity includes working across teams to optimize performance for Syntiant Neural Decision Processors, contributing to cutting-edge edge AI solutions.

Qualifications

• 8+ years of experience developing framework/applications of ML for edge devices.
• Strong background in C/C++ and Python.
• Experience with ML frameworks like TensorFlow and PyTorch.
• Familiarity with ML runtimes such as TVM, ONNX, and TensorRT.

Responsibilities

• Lead a team to develop model converter code for PyTorch and Keras.
• Work closely with the Machine Learning Modeling and Embedded Software teams.
• Optimize code for NDP, enhancing the DNN execution path where necessary.

Skills

C/C++ experience

Python experience

Experience with ML frameworks (e.g. TensorFlow, PyTorch)

Embedded development experience

Experience with code optimization

Job description

Summary Description:

Syntiant Corp., a leader in the high‑growth AI software and semiconductor solutions space, is looking for an experienced and talented Principal Software Engineer to take on a critical role with expansive responsibilities in the Core Machine Learning team.

As a Principal Software Engineer, you will lead a team to develop and enhance model converter code to support PyTorch and Keras trained models to run on Syntiant Neural Decision Processors. You will be interacting closely with the Machine Learning Modeling and Embedded Software teams to ensure that the trained models are efficiently converted for running on the NDP. You will apply your knowledge to optimize code and extract the last bit of performance from the NDP while generating the neural network model from a pretrained model. You will dig deep into embedded firmware code to optimize the DNN execution path if needed. You will be expected to work across the stack from model converter to embedded firmware, ultimately getting the opportunity to apply machine learning in real‑world applications and see your work driving the latest edge AI devices.

Qualifications, Education, and Experience Required:

• 8+ years of experience developing framework/applications of ML for edge devices.
• Strong C/C++ and Python experience.
• Experience with ML frameworks (e.g. TensorFlow, PyTorch).
• Experience with ML runtimes, e.g. TVM, ONNX, TF Lite Micro, TensorRT, etc.
• Experience in embedded development, bare metal and RTOS.
• Experience with code optimization, quantization, network pruning, etc.
• Experience working in large, complex codebases.

About Syntiant:

Founded in 2017 and headquartered in Irvine, Calif., Syntiant Corp. is a leader in delivering hardware and software solutions for edge AI deployment. The company’s purpose‑built silicon and hardware‑agnostic models are being deployed globally to power edge AI speech, audio, sensor and vision applications across a wide range of consumer and industrial use cases, from earbuds to automobiles. Syntiant’s advanced chip solutions merge deep learning with semiconductor design to produce ultra‑low‑power, high‑performance, deep neural network processors. Syntiant also provides compute‑efficient software solutions with proprietary model architectures that enable world‑leading inference speed and minimized memory footprint across a broad range of processors. The company is backed by several of the world’s leading strategic and financial investors including Intel Capital, Microsoft’s M12, Applied Ventures, Bosch Ventures, the Amazon Alexa Fund, and Atlantic Bridge Capital. More information on the company can be found by visiting www.syntiant.com.

One element in our total compensation package is base pay. Individual compensation decisions are based on a number of factors, including but not limited to previous experience and skills acquired prior to joining Syntiant, cost of living in the assigned work location, assigned schedule, and salaries of similarly situated peers at the company. It is to be expected that candidates will come to us with different sets of skills and experiences and therefore will be paid at different points in the stated range. We recognize that the person(s) we select for hire may be less experienced or more experienced than the role as posted; if this is the case, any updates to available salary ranges will be communicated with candidates during the recruitment process.