ML Ops Engineer

QuantHealth is an AI startup supporting drug development and clinical trials. Our ground-breaking clinical trial simulator can run thousands of trials in parallel to de-risk and optimize upcoming clinical trials. Our solution, based on a huge dataset of 350M patients and 100K drugs, drastically reduces drug development costs, shortens development timelines. We are venture backed, based in Israel, and have reputable pharma customers in both Europe and the US. This is a fantastic opportunity for an engineer who wants to join a fast-growing startup and tackle complex challenges.

Job Overview:

Our clinical trials simulator combines medical domain expertise, machine learning modeling, and statistical validation to simulate trials and predict their outcomes. We're seeking an experienced ML Ops Engineer to transform this process into a robust, production-grade system. This role requires deep machine learning knowledge to comprehend and enhance our ML lifecycle, combined with strong software engineering skills to design and implement a solution that orchestrates these complex workflows with reliability, reproducibility, and scalability. While this is fundamentally an IC position, it also heavily involves requirements gathering, software architecture, and effective communication with internal technical stakeholders.

Key Responsibilities:

• Work with stakeholders across our clinical data science, data science, engineering and commercial teams to understand current processes and future needs
• Full technical ownership of the clinical trial simulation system
• Design and implementation
• Data modelling for clinical trials simulations metadata
• Research and select appropriate tools and infrastructure
• Incorporate best practices such as CI/CD for ML models, model versioning, automated retraining, monitoring, validation automation, etc.
• Ensure reproducibility and scalability
• Manage technical approach and process for data science and clinical teams to integrate with the system
• Model integration, validation automation, etc.
• Tooling to enable trial and simulation metadata input
• Maintenance: change management, performance optimization, provide support, etc.
• Evolution: work with technical leaders across the org to align with long-term vision, scale team over time

Requirements:

• At least 5 years of experience in software development
• At least 2 years of experience developing AI systems or products
• Experience with Python backend development
• Experience with modern backend development concepts and tooling: SVC, containerization, package distribution, CI/CD pipelines, automated testing, etc.
• Experience with SQL and database design: data modelling, ORMs, migration tools, etc.
• Strong system design and software architecture skills
• Understanding of ML model lifecycle management and deployment: CI/CD for ML models, model retraining pipelines, automated validation, feature store management, etc.
• Experience with workflow orchestration tools such as Databricks Jobs, Apache Airflow or Delta Live Tables (DLT)
• Excellent communication and collaboration skills
• Ability to work independently and as part of a team

Advantage:

• Experience developing AI SaaS products
• Experience with Apache Spark and PySpark
• Familiarity with Databricks and MLFlow
• Knowledge of IaC tools such as Terraform
• Data engineering experience: ETL development, data warehousing, etc.
• Familiarity with clinical data and healthcare industry standards
• Familiarity with cloud platforms such as AWS, Azure, or GCP