Machine Learning Engineer, Inarix

• 3+ years of experience in Machine Learning Engineering or applied research, ideally in Computer Vision
• Strong grasp of the end-to-end ML lifecycle — from data understanding and processing to training iterations, post processing, evaluation, and thoughtful metric design
• Solid theoretical foundation in machine learning and image processing, with familiarity in modern architectures (e.g. Vision Transformers)
• Proficiency in Python and PyTorch, with hands-on experience running and debugging large experiments
• Proven ability to work with and analyze large and complex datasets (including embeddings), extracting actionable insights and improving data efficiency
• Comfortable balancing model accuracy, robustness, and computational constraints
• Curious, structured, and impact-oriented, with a focus on producing reliable, maintainable solutions
• Good written and spoken English
• Education Level: Master's Degree

Desirable

• Our mobile app Pocket Lab allows customers to take pictures of cereals and immediately access useful information about their quality
• Our digital solution has a radically different value and can both substitute existing solutions (hardware and/or expert analysis in laboratories) and extend what can be measured, providing new tools to help the agricultural sector face challenges such as fast quality assessment, supply-chain optimisation and traceability
• Under the hood, we run state-of-the art Deep Learning algorithms to estimate various criteria from images (variety, protein level, percentage of grains that are broken, etc.)
• We believe we have the world’s largest database of grain images, serving multiple purposes such as exploration, monitoring, labelling, and model training. We constantly update our modeling strategy with ideas coming from most recent papers or from our own experiments that make our products more robust and powerful
• Our online portal offers real-time data monitoring tools and analytics that assist our clients in managing their operations
• Join a Machine Learning team that sits at the core of Inarix’s technology, powering every product we build
• Unique data in a niche domain — you’ll work with proprietary, high-quality datasets rarely found elsewhere, enabling truly original modeling challenges
• The opportunity to build state-of-the-art AI systems that have tangible, real-world applications, bridging research and production, for which you’ll have a strong ownership
• A research-driven, engineering-minded ML team that values autonomy, technical depth, and meaningful results
• Access to solid computing infrastructure and the tools you need to iterate fast and experiment effectively
• A remote-first culture with access to our offices in Paris
• We’re looking for a Machine Learning Engineer with a passion for Computer Vision and Applied Research to join our ML team developing AI models for cereal analysis
• At Inarix, you’ll be at the core of our technology. Over the past years, and leveraging the latest advances in deep learning, we’ve built a unique set of techniques, tools, and models to transform images of grains into reliable, scalable insights
• Our technology, powered by a domain-specific grain foundation model, can already identify cereal varieties (sub-species of barley, wheat, corn, etc.) at the grain level, estimate protein or moisture content, and detect broken or other damages in grains — all from simple images
• You’ll work end-to-end: from data acquisition and labeling pipelines, to model design, training, deployment, and monitoring
• A significant part of your time will be dedicated to applied research, optimization, and system design, with the goal of improving both model performance and product robustness
• You’ll help design, train, and deploy models that power real products — combining scientific rigor with engineering pragmatism, with access to large proprietary datasets, advanced experimentation tools, and a team experienced in research and large-scale ML deployment
• Your work will directly impact product quality and model scalability, while shaping future product lines and use cases
• You'll work in an environment that values both deep research exploration and efficient, production-oriented AI — tackling niche yet high-impact applications where much remains to be discovered, including the development of foundation models built on our grain datasets
• This involves addressing challenges in multi-domain generalization, product-specific research, edge cases, and everything needed to make our models truly ready for production use
• Design, build, train, evaluate, and deploy computer vision models ready for production use, through iterative experimentation, focusing on solid metrics and reproducible results
• Contribute to the development of foundation models specifically trained on our large-scale grain datasets, advancing our ability to generalize across products and domains
• Collaborate across teams to translate high-level needs into clear ML objectives and measurable performance criteria
• For novel use cases, explore and validate new modeling strategies grounded in both academic insights and empirical testing
• Ensure production readiness through efficient pipelines, robust post-processing, and well-tested integrations
• Monitor and improve deployed models based on performance data and feedback from real-world usage
• Contribute to our ML core: shared tools, model evaluation frameworks, production inference system, and team-wide best practices
• Spend time to exploring new ideas — testing emerging methods, experimenting with alternative representations, and challenging existing assumptions to continuously improve our modeling capabilities
• Contract Type: Full-Time

• 1h with Hiring Manager
• 2h Technical interview
• 30 min with CTO
• 30 min with HR