Senior AI Programming Engineer

AI Programming Engineer 

Position overview: Ponchi is a new startup, founded in 2025, focused on developing AI inferencing chip. AI Programming Engineer plays central role in this endeavor. The company plans to hire one person in the role of senior AI Programming Engineer with strong expertise in language model inferencing. The employment can commence immediately. The company is specifically looking for candidates with strong understanding in developing innovative architecture, involving unconventional kernel optimization, that can be used in conjunction with proprietary chip data to reduce the size of Transformer network. 

Essential Duties and Responsibilities include the development of optimized procedure for AI inferencing using smaller network such as single layer to few layers of Transformer, writing codes to train the chip data, kernel computing, optimizing kernel for new AI hardware architecture, iteratively refine kernel design using profiling tools and feedback loops to achieve near-peak hardware utilization.

Requirements: Experience in optimization of network on AI hardware is desirable.  The person must have strong understanding of backpropagation method that can be utilized in hardware with FFN architecture. Also, the person must be capable of performing work independently, using advanced techniques, theories, and processes to complete work. 

Education & Experience: MS degree in Computer Science engineering or equivalent. 2+ years of experience will be preferred.

Salary: A highly competitive salary, commensurate to experience, will be provided.

Salary range: $120 K - $160 K

Sponsorship: The company does not sponsor. The person must be a US citizen, permanent resident or have work authorization and be open to relocation.

To apply: Send your CV/Resume and a cover letter, detailing expertise and work experiences, to recruiting@ponchi.ai