Bioscan Research
Website:
bioscanresearch.com
Job details:
Company Description Bioscan Research is dedicated to advancing early brain injury detection through innovative, non-invasive technologies. For over a decade, the team has focused on supporting timely identification and triage of traumatic brain injury with its flagship device, CEREBO®, which uses near-infrared spectroscopy and adaptive machine learning to assist clinicians in detecting intracranial haemorrhage at the point of care. Designed for emergency, defence, and public health settings, CEREBO® enables rapid screening where access to CT imaging is limited. Bioscan Research designs and manufactures its technology in-house, integrating proprietary optical systems, embedded electronics, and advanced signal-processing algorithms, and validates these solutions through deployments in hospitals and premier institutes. Guided by scientific integrity and clinical collaboration, the multidisciplinary team works to strengthen emergency and neurocritical care infrastructure in India and beyond.
Role Description
The AI & Clinical Data Science Engineer is a full-time, on-site role based in Ahmedabad and will lead the end-to-end development, validation, and deployment of artificial intelligence solutions across Bioscan Research's portfolio of neurotechnology products and future digital health platforms. The role is responsible for transforming biomedical signals, clinical data, and real-world evidence into clinically meaningful algorithms supporting diagnosis, patient monitoring, clinical decision support, and neuroscience research.
Working closely with hardware, firmware, software, clinical, and regulatory teams, the engineer will design and implement data pipelines for acquiring, processing, storing, and analysing multimodal clinical and device-generated data; develop and validate AI models through phantom studies, animal studies, and human clinical trials; and deploy scalable algorithms across embedded devices, cloud platforms, and software applications. The role also includes supporting clinical studies, ensuring data quality and regulatory compliance, maintaining technical documentation, and continuously improving AI models using real-world clinical data.
Key Responsibilities1. AI Algorithm DevelopmentKey Responsibilities:
-- AI Algorithm Development
- Develop machine learning, deep learning, signal processing, and predictive analytics models across Bioscan's product portfolio for Clinical Decision Support Systems, Research SDKs and developer platforms
- Translate clinical and product requirements into measurable algorithm objectives and performance targets.
- Develop feature engineering pipelines, biomarkers, classification models, prediction models, and risk scoring algorithms.
- Build decision-support algorithms for patient triage, monitoring, deterioration prediction, risk stratification, and treatment recommendations.
- Develop multimodal AI architectures combining multiple data streams into clinically actionable outputs.
-- Experimental Design & Clinical Validation
- Design and execute validation studies using phantom models, Bench-top experiments, Animal studies, Healthy volunteer studies and Human clinical trials
- Develop validation protocols, statistical analysis plans, and performance evaluation frameworks.
- Compare model performance against clinical reference standards including imaging, biomarkers, and clinician assessments.
- Analyse validation data and iteratively improve algorithms.
-- Data Engineering & Dataset Development
- Build pipelines for data acquisition, preprocessing, annotation, storage, and model training.
- Collaborate with Clinical Affairs to curate high-quality datasets for algorithm development.
- Ensure data quality, traceability, reproducibility, and regulatory compliance.
-- AI Deployment & Product Integration
- Deploy models to embedded systems, mobile applications, cloud platforms, and hospital information systems.
- Optimise algorithms for real-time performance, computational efficiency, reliability, and scalability.
- Collaborate with firmware, software, and cloud teams to integrate AI into commercial products.
- Monitor model performance and support post-market improvements.
-- Research SDK & Developer Platform Development
- Develop SDKs, APIs, reference algorithms, and developer tools for proprietary hardware research platforms.
- Create technical documentation, sample datasets, and software libraries to enable external researchers to build novel applications.
-- Regulatory & Technical Documentation
- Contribute to Design History Files, software documentation, algorithm specifications, verification reports, validation reports, risk management files, and clinical performance reports.
- Support compliance with FDA Good Machine Learning Practice (GMLP), IEC 62304, ISO 14971, and ISO 13485 requirements.
-- Research & Innovation
- Evaluate emerging AI methodologies, signal processing techniques, and foundation models relevant to neuroscience and medical devices.
- Support scientific publications, patents, grant proposals, and technical presentations.
- Benchmark Bioscan algorithms against current state-of-the-art approaches.
Skills & Experience:
- Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Data Science, Biomedical Engineering, Electronics Engineering, Mathematics, Statistics, or a related field.
- Strong understanding of machine learning, deep learning, statistical modelling, and multimodal AI for healthcare applications.
- Experience in biomedical signal processing, time-series analysis, feature engineering, predictive analytics, and clinical data analysis.
- Proficiency in Python and AI/ML frameworks such as PyTorch, TensorFlow, and Scikit-learn; experience with SQL and data engineering is desirable.
- Experience designing and implementing data pipelines for acquisition, preprocessing, annotation, storage, and analysis of clinical and device-generated data.
- Knowledge of experimental design, biostatistics, AI model validation, and performance evaluation using retrospective and prospective clinical datasets.
- Experience deploying AI models on embedded devices, cloud platforms, and software applications; familiarity with MLOps, model version control, and deployment pipelines is preferred.
- Understanding of medical device software development, Software as a Medical Device (SaMD), and AI integration into regulated medical devices.
- Familiarity with medical device regulatory standards and documentation, including ISO 13485, IEC 62304, ISO 14971, FDA Good Machine Learning Practice (GMLP), and AI validation documentation.
- Strong scientific writing, technical documentation, analytical thinking, and problem-solving skills.
- Excellent communication, collaboration, and project management skills with the ability to work effectively in multidisciplinary teams comprising engineering, clinical, regulatory, and product development functions.
Click on Apply to know more.