At Sword we’re building AI to heal billions and unlock humanity’s full potential. In doing so we’re pioneering AI Care a fundamentally new approach to healthcare built for medical reasoning safety and real-time treatment not generic technology applied after the fact. As both a clinical-centric frontier AI lab and an applied AI platform Sword is reimagining how care is delivered at scale removing traditional barriers like appointments waiting rooms and stigma so more people can access the care they need - and ultimately get back to lives lived in full. Since 2020 Sword has expanded across Musculoskeletal Women’s Health Cardiometabolic and Mental Health and is now moving beyond the session to a fully AI-native 24/7 care program that brings physical activity therapeutic exercise psychotherapy nutrition and behavior change into one connected experience. More than 1 million members across three continents have completed over 15 million AI sessions helping 2000+ enterprise clients avoid more than $1 billion in unnecessary healthcare costs. Backed by 59 clinical studies 43 patents and more than $500 million raised from leading investors including Khosla Ventures General Catalyst and Founders Fund Sword is defining a new standard for healthcare. Role Thrive is Sword's program for chronic joint and back pain personalized clinician-designed physical therapy delivered at home with an AI care specialist guiding members between visits. What makes it work is movement understanding. During each session Thrive reads how a member moves from the camera and gives real-time feedback on their exercises the way a physical therapist in the room would. The Computer Vision team part of the Algorithms org builds the models behind that. We turn a camera feed into an accurate read of human movement 2D and 3D pose and body dynamics in real time on-device or in-the-cloud and turn that movement into clinical signals. This role owns that computer vision end to end the models the data lifecycle that feeds them the evaluation and the systems that ship them to members at scale. ### What you'll be doing Own core computer vision models from 3D human pose to statistical body modeling taking them from prototype to production Ship those models to run real-time in the cloud and on-device on tablets owning the conversion and optimization in between Own the data and code lifecycle behind them training frameworks annotation workflows pipelines auto-labeling test sets and taxonomy Extend movement understanding into multimodal territory combining it with language and reasoning build novel approaches in the movement-intelligence domain Unify and mature how we train track version and deploy models so every result is reproducible and testable Design systems that run without you automating the loops so the team's output scales past manual effort Help grow the Computer Vision team by defining and promoting best practices establishing principles that scale your impact. ### What you need to have 5+ years solving complex problems with Computer Vision with models shipped to production Strong software engineering foundation across architecture pipelines MLOps and the full model lifecycle Deep hands-on command of modern Computer Vision (transformers and convolutional models) with real depth in at least one of detection segmentation tracking pose or 3D A data-centric instinct you cook your own data build data flywheels and active-learning loops and treat the dataset as source code Solid grounding in multimodal AI with the ability to build systems that pair vision with language and reasoning when the problem calls for it Strong written asynchronous communication. You think in specs and documents and leave a clear trail others can build on Self-direction and full ownership you scope ambiguity into a plan and ship without being told Fluency with PyTorch or JAX the Python data stack and comfort picking up new languages and codebases AI-native ways of working you build AI into the workflow itself from agents to LLM-in-the-loop tooling. ### What we would love to see Experience with pose estimation body modeling movement intelligence or human-motion work Experience working with massive data building full-lifecycle ML systems at a startup or scaleup wearing different hats Experience automating experimentation or model-improvement loops Product mindset users empathy and desire to ship impact to millions of members. This range includes base variable and equity These compensation bands are just the starting point. Once someone joins and proves they’re outlier talent we adjust quickly to ensure their compensation aligns with their impact. Our job titles may span more than one career level. Actual pay is determined by skills qualifications experience location market demand and other factors. Compensation details listed in this posting reflect the base salary and any potential variable bonus or sales incentives and the Company’s estimation of the value of private company stock options if applicable. The pay range is subject to change future value of company stock options is not guaranteed and compensation may be modified in the future. In addition to our total compensation Sword offers a number of benefits as listed below. Portugal - Sword Benefits & Perks Health dental and vision insurance Meal allowance Equity shares Remote work allowance Flexible working hours Work from home Discretionary vacation Snacks and beverages Note Please note that this position does not offer relocation assistance. Candidates must possess a valid EU visa and be based in Portugal. Sword Health complies with applicable Federal and State civil rights laws and does not discriminate on the basis of Age Ancestry Color Citizenship Gender Gender expression Gender identity Gender information Marital status Medical condition National origin Physical or mental disability Pregnancy Race Religion Caste Sexual orientation and Veteran status. We may use artificial intelligence (AI) tools to support parts of the hiring process such as reviewing applications analyzing resumes or assessing responses and identifying potential inconsistencies or verification signals in application materials based on available information. These tools assist our recruitment team but do not replace human judgment. Final hiring decisions are ultimately made by humans. If you would like more information about how your data is processed please contact us.