Python​/PyTorch Developer — Frontend Inference Compiler

Position: Staff Python / PyTorch Developer — Frontend Inference Compiler
# Staff Python PyTorch Developer Cerebras Systems, Inc.

Sharjah, AEPosted 7/1/2026### AI Match Score Based on your profile & preferences 0%
Looking for a
** Staff Python PyTorch Developer
** role in
** Sharjah, AE**? This position at
** Cerebras Systems, Inc.
** is an excellent opportunity for professionals looking to advance their career. Browse the full job description below to see if you're a match and add it to your board.###

Job Description

About the Role:

- Design and implement APIs, machine learning features, and tools for generative AI models on custom hardware.

- Provide technical guidance to software engineers on complex ML integration projects.

- Design high-throughput, low-latency multimodal inference models supporting image, audio, and video.

- Maintain scalable serving backend handling many concurrent requests.

- Implement observability across the inference stack.

- Analyze and improve latency, throughput, memory usage, and compute efficiency.

- Optimize software for generative LLM inference.

- Stay updated with ML and deep learning advancements.

- Evaluate trade-offs and develop proposals for new features.

- Manage technical debt to ensure software quality.

- Build and maintain automated test suites.

- Contribute to agile team environment.

- Lead cross-functional initiatives for inference solutions.

Skills &

Qualifications:

- Bachelor’s, Master’s, or PhD in Computer Science, Computer Engineering, Mathematics, or related field.

- 8+ years experience in large-scale software engineering focused on deep learning or related domains.

- Proficiency in Python.

- Advanced proficiency in C++ with multi-threaded programming and performance optimization.

- Experience driving cross-functional projects.

- Experience building and scaling large-scale inference systems.### Ace the Cerebras Systems, Inc. Interview Our AI has generated the most probable interview questions for this role based on the job description and industry standards.

Technical Execution & Core Skills How would you design and implement a high-throughput, low-latency multimodal inference model for generative AI?

Problem-solving & Adaptability Describe a situation where you identified and prioritized technical debt in a large-scale inference system and how you addressed it.

Communication & Teamwork Explain how you have led cross-functional initiatives to deliver high-quality machine learning inference solutions.
#J-18808-Ljbffr