Senior MLOps Engineer - Edge
在 Hudl,我们建立出伟大的团队。我们聘请最好的最佳人员以确保你与可以不断学习的人一起工作。你有信心在测试可能和下一步的极限时完成自己的工作。我们努力为每个人都感到支持的文化提供服务，我们的员工觉得他们的投票帮助我们成为新闻周刊100强大全球最受欢迎的工作场所之一。我们认为自己是团队背后的团队，支持终身影响运动：团队合作和奉献精神的教训；鼓舞人心的教练的影响；以及新高点的机会。这就是为什么我们帮助世界各地的团队以不同的方式看待他们的比赛。我们的产品使任何级别的教练和运动员更容易捕捉视频，分析数据，分享亮点等。准备加入我们？你的角色 我们正在聘请一名高级 MLOps 工程师来组建和扩展 Focus,我们的智能摄像头系列的机器学习基础设施。作为高级 MLOps 工程师，你将：· 构建可扩展的 Edge 基础设施。你将设计，开发和维护使我们能够部署模型到设备队伍中的传输系统。· 拥有模型编译平台。• 专业技术人员将在该领域提供服务。你将建立和维护采用训练有素的模型生产优化硬件特定推理引擎的管道。管理 TensorRT 编译，精度交易 (FP16/INT8),校准和发动机验证以确保模型在目标设备上可靠有效运行。· 与跨功能团队合作。你将与数据科学家，嵌入式工程师和产品经理合作，以确保复杂特性和能力的流整合。·驱动自动化和可靠性。你将实施基础设施来默认测试生产设备上的候选型号，并构建远程测量管道来监控漂移，热效影响和推断在野外。· 解决复杂的物理挑战。你将应对边缘独特的限制 - - 为低带宽环境建立弹性更新机制，为有限的存储优化，以及
查看英文原文
At Hudl, we build great teams. We hire the best of the best to ensure you’re working with people you can constantly learn from. You’re trusted to get your work done your way while testing the limits of what’s possible and what’s next. We work hard to provide a culture where everyone feels supported, and our employees feel it—their votes helped us become one of Newsweek's Top 100 Global Most Loved Workplaces.
We think of ourselves as the team behind the team, supporting the lifelong impact sports can have: the lessons in teamwork and dedication; the influence of inspiring coaches; and the opportunities to reach new heights. That’s why we help teams from all over the world see their game differently. Our products make it easier for coaches and athletes at any level to capture video, analyze data, share highlights and more.
Ready to join us?
Your Role
We're hiring a Senior MLOps Engineer for our Hardware Group to build and scale the machine learning infrastructure that powers Focus, our line of smart cameras. You'll own the edge deployment pipelines that transport neural networks from training clusters to tens of thousands of devices globally, and contribute to the platform that compiles trained models into optimised inference engines for devices like the Jetson Orin, building the "nervous system" for the next generation of automated sports capture.
As a Senior MLOps Engineer, you'll:
- Build scalable Edge infrastructure. You'll design, develop, and maintain the delivery systems that enable us to deploy models to fleets of devices.
- Own the model compilation platform. You'll build and maintain the pipeline that takes trained models and produces optimised, hardware-specific inference engines — managing TensorRT compilation, precision trade-offs (FP16/INT8), calibration, and engine validation to ensure models run reliably and efficiently on target devices.
- Work with cross-functional teams. You'll collaborate with Data Scientists, Embedded Engineers, and Product Managers to ensure smooth integration of complex features and capabilities
- Drive automation and reliability. You'll implement infrastructure to silently test candidate models on production devices and build telemetry pipelines to monitor drift, thermal impact, and inference latency in the wild.
- Solve complex physical challenges. You'll tackle the unique constraints of the edge - building resilient update mechanisms for low-bandwidth environments, optimising for limited storage, and ensuring devices recover gracefully from network failures.
- Mentor and lead. You'll share your expertise to establish best practices in Python tooling, Infrastructure-as-Code, and CI/CD, guiding the team toward a more robust, automated future.
We'd like to hire someone for this role who lives near our offices in London or Barcelona, but we're also open to remote candidates in the UK and Spain.
Must-Haves
- Production MLOps expertise. You've played a key role in building and operating pipelines that deploy models to production, with deep experience in CI/CD, containerization (Docker), and Linux systems.
- Edge inference & compilation know-how. You have hands-on experience compiling and optimising models for embedded hardware - ideally with TensorRT - and understand the practical implications of precision, quantisation, and engine validation at scale.
- Collaborative. You understand that shipping to hardware is a team sport and can communicate effectively with researchers and low-level embedded engineers to translate constraints into solutions.
- Systems thinking. You can design architectures that handle failure gracefully and understand the implications of deploying to 10,000 heterogeneous devices, including how to manage risk via canary releases and safe rollbacks.
- Bias towards action. You see your role as solving problems; this means filling gaps and taking initiative as needed to help the team win together.
Nice-to-Haves
- Experience with our Edge AI stack. Experience with the NVIDIA edge ecosystem (Jetson Orin, DeepStream SDK, TensorRT) is a huge plus.
- Video Technologies. Familiarity with video pipelines, GStreamer, or ffmpeg.
- Fleet management. Experience with tools like AWS IoT Greengrass, Balena, or custom OTA / fleet management solutions.
- Sports Passion. You have an interest in sports technology, video analytics, or performance metrics—but if not, we'll teach you the domain.
Our Role
- Champion work-life harmony. We’ll give you the flexibility you need in your work life (e.g., flexible vacation time, company-wide holidays and timeout (meeting-free) days, remote work options and more) so you can enjoy your personal life too.
- Guarantee autonomy. We have an open, honest culture and we trust our people from day one. Your team will support you, but you’ll own your work and have the agency to try new ideas.
- Encourage career growth. We’re lifelong learners who encourage professional development. We’ll give you tons of resources and opportunities to keep growing.
- Provide an environment to help you succeed. We've invested in our offices, designing incredible spaces with our employees in mind. But whether you’re at the office or working remotely, we’ll provide you the tech stack and hardware to do your best work.
- Support your wellbeing. Depending on location, we offer medical and retirement benefits for employees—but no matter where you’re located, we have resources like our Employee Assistance Program and employee resource groups to support your mental health.
Compensation
Inclusion at Hudl
Hudl is an equal opportunity employer. Through our actions, behaviors and attitude, we’ll create an environment where everyone, no matter their differences, feels like they belong.
We offer resources to ensure our employees feel safe bringing their authentic selves to work, including employee resource groups and communities. But we recognize there’s ongoing work to be done, which is why we track our efforts and commitments in annual inclusion reports.
We also know imposter syndrome is real and the confidence gap can get in the way of meeting spectacular candidates. Please don’t hesitate to apply—we’d love to hear from you.
Privacy Policy
Hudl Applicant and Candidate Privacy Policy
Originally posted on Himalayas