5 months ago
Gurgaon, IndiaStaff+
Responsibilities
- Design, train, evaluate, benchmark, and tune computer vision models for live video and multi-camera use cases.
- Curate datasets and build training, validation, and testing pipelines for detection, classification, segmentation, and tracking models.
- Optimize models through architecture changes, quantization, pruning, and distillation to meet deployment and scaling constraints.
- Maintain and upgrade production models by triaging regressions, refreshing training data, addressing drift, and shipping improved versions.
- Design, build, and ship a native Android application that interacts with the cloud backend.
- Implement secure Android cloud integration, offline-first synchronization, runtime permissions, and background execution.
- Set up Android CI, unit and instrumentation testing, crash reporting, and Play Store release pipelines.
- Collaborate with deployment, MLOps, operations, and maintenance teams and interface with embedded or IoT hardware over BLE and Wi-Fi.
Requirements
- 5+ years of total professional software engineering experience.
- Proven experience training and testing vision-based models that have been shipped to production.
- Hands-on experience with cloud-based AI training and experimentation infrastructure such as AWS SageMaker, GCP Vertex AI, or Azure ML.
- Experience developing models for continuous live-video monitoring and efficient inference across multiple concurrent camera streams.
- Experience translating deployment and runtime constraints into model decisions and supporting models after launch.
- Proficiency in Python and ML frameworks including PyTorch, TensorFlow, TensorFlow Lite, and ONNX, with a strong understanding of CNNs and modern detection and tracking architectures.
- Strong proficiency in Kotlin and the modern Android stack, with experience shipping production Android apps to the Play Store.
- Deep knowledge of Android Wi-Fi and BLE APIs, Android security and permissions, foreground services, and background execution limits.
- Experience with Android cloud connectivity, including REST, gRPC, WebSockets or MQTT, OAuth2/JWT, TLS, and FCM.
- Experience interfacing with embedded or IoT hardware over BLE and Wi-Fi under intermittent connectivity, retry, and power constraints.
- Preferred experience with Android NNAPI, Qualcomm SNPE, MediaPipe, GPU delegates, RTSP, WebRTC, HLS, video codecs, edge or IoT camera deployments, model monitoring, drift detection, active learning, or open-source ML and Android projects.
- Bachelor’s or master’s degree in Computer Science, AI/ML, or a related field, or equivalent practical experience.
- Strong product mindset, measurement focus, collaboration skills, and ability to work across ML model development and Android application development.
Benefits
- Hybrid or onsite work arrangement.
- Approximately 10% travel.
- Bachelor’s or master’s degree requirement may be satisfied by equivalent practical experience.
Categories
ML EngineeringMobile
About Stryker
Stryker designs and manufactures medical devices and equipment for hospitals and surgeons, spanning orthopaedic implants, trauma and spine hardware, surgical tools, endoscopy, navigation, and patient care equipment. The NYSE-listed company, founded in 1941 and headquartered in Kalamazoo, Michigan, sells products and related services worldwide to health systems and ambulatory centers. It reported $22.6 billion in 2024 sales and markets its portfolio across roughly 75 countries.