独家首发！端侧机器学习高级工程师 JD 震撼来袭！（双语阅读）

这本文首发于微信公众号：On-Device AI，欢迎关注，在这里，我们聚焦于设备上生成式人工智能的最新进展、技术深度解析、应用案例分享及未来趋势展望。

Description For Senior Software Engineer - On-Device ML

As an On-Device Machine Learning (ML) Frameworks Engineer at Dynamo AI, you will play a crucial role in developing and optimising machine learning models to run efficiently on various devices such as smartphones, tablets, AI PC and embedded systems. Your work will involve collaborating with cross-functional teams to integrate ML models into applications, ensuring they are both effective and resource-efficient. This role is vital in pushing the boundaries of what’s possible with on-device AI, contributing to the enhancement of user experiences and the innovation of new features.

高级软件工程师 - 端侧机器学习岗位描述

作为 Dynamo AI 的端侧机器学习（ML）框架工程师，您将在开发和优化机器学习模型以在各种设备（如智能手机、平板电脑、AI PC 和嵌入式系统）上高效运行的工作中发挥关键作用。您的工作将涉及与跨职能团队合作，将 ML 模型集成到应用程序中，确保它们既高效且资源占用率低。这一角色对于推动端侧 AI 的可能性边界至关重要，有助于提升用户体验和新功能的创新。

Responsibilities:

• Optimize machine learning models, ML Graph Conversion Stack & ML Inference Stack for deployment on edge devices.
• Develop and maintain OnDevice ML Inference Framework for specialized and general purpose processors.
• Collaborate with software engineers, data scientists, and product managers to integrate ML solutions into products.
• Implement techniques to ensure efficient inference and minimal resource consumption on target devices.
• Conduct performance evaluations and continuous improvement of ML models & Inference pipeline post-deployment.
• Stay updated with the latest advancements in on-device ML technologies and frameworks.
• Troubleshoot and resolve issues related to ML model deployment and execution on devices.

岗位职责：

• 优化机器学习模型、ML Graph Conversion Stack 和 ML Inference Stack，以便在边缘设备上部署。
• 开发和维护针对专用和通用处理器的端侧 ML 推理框架。
• 与软件工程师、数据科学家和产品经理合作，将 ML 解决方案集成到产品中。
• 实现相关技术以确保在目标设备上高效推理和最小化资源消耗。
• 进行性能评估，并对部署后 ML 模型及推理管道的持续改进。
• 保持对端侧 ML 技术和框架的最新进展的了解。
• 定位和解决与端侧 ML 模型部署和执行相关的问题。

Qualifications:

• Strong programming skills in languages such as C++, C and Python.
• Must have experience with in-depth working and core implementation of machine learning frameworks such as TensorFlow Lite, PyTorch Mobile, ONNX or Core ML.
• Strong experience and proven track record with intrinsic level (SIMD, NEON, AVX) implementation for optimizing compute and memory algorithms.
• Proven track record of deploying ML models on edge devices and optimizing them for performance and memory.
• Familiarity with performance profiling tools and techniques for mobile and embedded platforms.
• Solid understanding of computer architecture and hardware acceleration techniques.
• Effective communication skills and the ability to work collaboratively in a team environment.
• Bachelor’s or Master’s degree in Computer Science, Electronics Engineering, or a related field.

任职资格：

• 精通 C++、C 和 Python 等编程语言。
• 必须具有机器学习框架（如 TensorFlow Lite、PyTorch Mobile、ONNX 或 Core ML）的深入使用和核心实现经验。
• 具有指令级别（SIMD、NEON、AVX）实现优化计算和内存算法的丰富经验和成功经验。
• 在边缘设备上部署 ML 模型并优化其性能和内存的成功经验。
• 熟悉移动和嵌入式平台的性能分析工具和技术。
• 对计算机架构和硬件加速技术有扎实的理解。
• 有效的沟通技巧和在团队环境中协作工作的能力。
• 计算机科学、电子工程或相关领域的学士或硕士学位。

Dynamo AI is committed to maintaining compliance with all applicable local and state laws regarding job listings and salary transparency. This includes adhering to specific regulations that mandate the disclosure of salary ranges in job postings or upon request during the hiring process. We strive to ensure our practices promote fairness, equity, and transparency for all candidates.

Dynamo AI 致力于遵守所有适用的地方和州法律，关于职位列表和薪资透明度的规定。这包括遵守特定法规，这些法规要求在招聘过程中的职位发布或请求时披露薪资范围。我们努力确保我们的实践促进所有候选人的公平、平等和透明度。

Salary for this position may vary based on several factors, including the candidate’s experience, expertise, and the geographic location of the role. Compensation is determined to ensure competitiveness and equity, reflecting the cost of living in different regions and the specific skills and qualifications of the candidate.

此职位的薪资可能因多种因素而异，包括候选人的经验、专业知识和角色的地理位置。确定的薪酬旨在确保竞争力和公平性，反映不同地区的生活成本和候选人的具体技能和资格。

原文链接：https://www.jointaro.com/jobs/dynamo-ai/senior-software-engineer-on-device-ml/