Software Engineer, AI/ML

We are seeking a Software Engineer with over two years of experience and a solid background in Machine Learning and Computer Vision to contribute to an innovative health tech project. This role involves developing real-time AI assistance for clinicians performing ultrasound-guided endoscopic procedures. The system processes live ultrasound video to identify anatomy, suspected pathology, and medical instruments on a frame-by-frame basis, providing clinicians with insights into the AI model’s focus during procedures. This position offers hands-on involvement throughout the segmentation model lifecycle, from working with curated clinical data and model training to evaluation, optimization, deployment, retraining, and close collaboration with clients.

Key Responsibilities

- Train and enhance multi-label medical image segmentation models using PyTorch.
- Handle ultrasound video datasets alongside clinician-annotated medical imaging data.
- Conduct experiments addressing challenges such as class imbalance, overlapping anatomy, small or thin targets, and temporal context.
- Develop and refine evaluation pipelines with metrics at per-label, frame-level, and event-level granularity.
- Validate models using patient-level test splits and clinician feedback.
- Optimize inference for real-time video processing, focusing on GPU latency and performance.
- Utilize techniques like mixed precision, model compilation, batching, and frame stride to improve inference efficiency.
- Package and deploy models using Docker and AWS-based infrastructure.
- Contribute to reproducible training and retraining pipelines incorporating experiment tracking, checkpointing, continuous integration, and automated testing.
- Collaborate closely with clinicians, annotators, infrastructure engineers, and external machine learning partners.
- Participate actively in client meetings, technical discussions, demos, requirement gathering, and progress updates.
- Clearly communicate technical decisions, experiment outcomes, risks, and trade-offs to both technical and non-technical stakeholders.
- Work directly with clients to gather feedback, clarify requirements, and translate discussions into actionable engineering tasks.

Required Qualifications

- Bachelor’s degree in Computer Science, Artificial Intelligence, or a related field.
- Minimum of 2 years of relevant experience in software engineering, machine learning, or computer vision.
- Proficient in Python programming with hands-on experience using PyTorch.
- Experience training image segmentation or computer vision models.
- Strong understanding of model training, validation, evaluation, and inference workflows.
- Familiarity with data loaders, mixed precision training, checkpointing, and GPU-based training.
- Knowledge of video or image-based datasets and best practices for train-test data separation.
- Experience or familiarity with AWS, cloud GPU environments, object storage, and Docker.
- Understanding of production ML inference and performance optimization.
- Solid software engineering fundamentals, including testing, version control, reproducible configurations, and continuous integration.
- Excellent verbal and written communication skills.
- Confidence in participating in client meetings and technical discussions.
- Ability to explain technical topics clearly, ask insightful questions, and proactively communicate blockers or risks.
- Capability to discuss experiments, model results, implementation decisions, and trade-offs directly with clients.

Preferred Qualifications and Benefits

Preferred candidates will have experience with medical imaging or medical image segmentation, medical video annotation platforms, and real-time computer vision or video inference. Familiarity with multiple segmentation architectures or frameworks, multi-GPU training, model deployment, and inference optimization is advantageous. Prior experience working directly with clients, product teams, or external stakeholders is highly valued. Awareness of Software as a Medical Device (SaMD) practices, model traceability, model cards, audit trails, or clinical acceptance processes is a plus.

Benefits include Provident Fund, comprehensive medical inpatient and outpatient facilities, paid overtime, subsidized lunch and dinner, gym access, sports allowance, interest-free loan facility, advance salary options, and various employee engagement activities.

If you have practical experience in computer vision and PyTorch, enjoy client interaction, and are passionate about applying AI to real-time clinical workflows, we encourage you to apply.