Senior Inference Engineer

About The Company

Roboflow is a leading innovator in the field of computer vision and AI technology, dedicated to transforming industries through advanced machine learning solutions. With a distributed team across the United States and Europe, Roboflow fosters a collaborative and dynamic environment that encourages innovation, open-source contributions, and continuous learning. The company offers a range of products and services that empower developers and organizations to build, deploy, and scale computer vision applications efficiently. Roboflow’s commitment to open source, combined with its focus on cutting-edge AI research and practical deployment, positions it as a pioneer in the AI ecosystem, enabling impactful solutions across various sectors including manufacturing, retail, healthcare, and more.

About The Role

The Inference Engineer at Roboflow plays a pivotal role in enhancing and maintaining the company’s flagship computer vision inference engine, ensuring it remains robust, scalable, and high-quality as contribution volumes increase. This role is essential for building an automated and semi-automated contribution pipeline that streamlines review, triage, CI/CD, and testing processes, ultimately enabling the team to transition from weekly to nightly releases. The engineer will be responsible for designing and expanding a comprehensive test suite that validates build health across multiple targets, both standalone and on-platform, ensuring reliability and performance. Additionally, this role involves defining review standards, implementing guardrails for AI agents, and simplifying the process of integrating new models into the inference engine. The Inference Engineer will also serve as a technical ambassador, educating internal teams and customers on leveraging Roboflow’s AI capabilities, contributing to open source projects, and fostering a vibrant community around the platform. This position offers a unique opportunity to shape the future of AI-driven contributions and releases at Roboflow, making a tangible impact on the company's growth and the broader AI community.

Qualifications

• 5+ years of hands-on experience building and operating production-grade machine learning systems, particularly involving large-scale AI model deployment.
• Deep understanding of computer vision models, inference processes, and deployment strategies across diverse environments.
• Proficiency in AI coding agents, with a proven track record of automating engineering workflows such as review, triage, testing, and CI/CD.
• Strong computer science background with the ability to solve complex architecture and reliability challenges.
• Experience with CI/CD pipelines, release engineering, and automated testing infrastructure.
• Practical knowledge of core ML technologies including PyTorch, TensorFlow, ONNX, TensorRT, and model deployment tools like vLLM.
• Expertise in image and video processing, with familiarity in OpenCV, DeepStream, Pillow, PyAV, and hardware-accelerated decoding; experience with video streaming protocols is a plus.
• Excellent communication skills, with the ability to teach, write, and collaborate effectively across teams and with external stakeholders.

Interested in remote work opportunities in Machine Learning & AI? Discover Machine Learning & AI Remote Jobs featuring exclusive positions from top companies that offer flexible work arrangements.

• Experience in open source project maintenance and community engagement is highly desirable.
  
  

Responsibilities

• Build, maintain, and improve the inference engine to ensure high quality and scalability as contribution volume grows.
• Design and implement an agentic-driven contribution pipeline that automates review, triage, and CI/CD processes, facilitating more frequent releases.
• Develop and expand a comprehensive, real-world test suite that validates build health across all targets, aiming for nightly end-to-end testing.
• Establish and enforce review standards and guidelines, exercising sound judgment on merge decisions, and encoding these standards into automated systems.
• Simplify and accelerate the process of integrating new models into the inference engine, making it easier and faster to deploy the latest computer vision and ML models.
• Educate and support internal teams and customers to maximize the value derived from Roboflow’s AI tools, including creating documentation, demos, and tutorials.
• Act as a bridge between core engineering and clients, translating technical capabilities into accessible content and product launches.
• Contribute to the open source community by maintaining repositories, engaging with contributors, and promoting collaborative development.
  
  

Benefits

• Competitive salary aligned with market standards, reviewed biannually.
• Travel stipend of $4000/year for in-person collaboration and team events.
• Monthly stipends for productivity ($350), AI tools ($350), and team lunches ($150).
• Comprehensive health insurance coverage for employees and their families, covering up to 100% of costs.
• Remote-first work environment with flexible scheduling, supporting work from home, co-working spaces, or company hubs.
• Unlimited paid time off with a minimum of two weeks annually to encourage work-life balance.
• 12 weeks of parental leave to support family growth and caregiving needs.
• Equity ownership in the company, aligning employee success with company growth and innovation.
  
  

Equal Opportunity

Roboflow is an equal opportunity employer. We celebrate diversity and are committed to creating an inclusive environment for all employees. We do not discriminate based on race, ethnicity, gender, sexual orientation, age, disability, religion, or any other protected status. All qualified applicants will receive consideration for employment without regard to these factors, and we are dedicated to fostering a workplace where everyone can thrive and contribute to our mission of advancing computer vision technology.