ML Engineer, CloudlyCare

Job Description

As ML Engineer for CloudlyCare, you will work on one of the most technically demanding and consequential AI systems in our portfolio. You will develop, evaluate, and improve the ML models that sit inside our multi-agent clinical architecture, with an uncompromising focus on safety, accuracy, and auditability. Every model you build influences clinical recommendations that affect patient outcomes. That weight shapes everything about how we work: how we evaluate, how we validate, and how we deploy.

ABOUT CLOUDLYCARE
CloudlyCare is an Agentic Clinical Decision Support System built on a hierarchical multi-agent architecture spanning 7 specialized agents and 11 medical domains. It delivers a sub-0.1% hallucination rate, evidence-based recommendations with confidence scores on every output, five-layer drug safety checking, and full FHIR R4 EHR integration with Epic, Cerner, and others. Validated across 12 clinical scenarios with 92.3% diagnostic accuracy and 89% reduction in prescription errors, CloudlyCare is built to augment clinicians without ever removing them from the final decision.

Job Requirement

  • Develop and improve ML models within CloudlyCare's hierarchical multi-agent architecture across clinical domains including diagnostics, pharmacology, cardiology, mental health, pediatrics, and others
  • Design and implement accuracy climbing techniques that push diagnostic accuracy while maintaining calibrated confidence scores on every model output
  • Build and maintain hallucination detection and mitigation systems targeting the sub-0.1% hallucination rate that CloudlyCare's clinical safety standards require
  • Develop and improve the five-layer drug safety checking system, incorporating drug interaction detection, contraindication flagging, and dose verification
  • Work with clinical advisors and domain experts to define evaluation criteria, build clinically relevant test sets, and validate model outputs against established medical guidelines
  • Implement human-in-the-loop escalation mechanisms that trigger appropriately when model confidence falls below defined thresholds
  • Build evidence citation systems that attach verifiable sources to every recommendation the system produces
  • Maintain and improve model compliance with HIPAA and EU healthcare AI regulations, ensuring all outputs are auditable, explainable, and traceable
  • Monitor model performance in production and build retraining pipelines that maintain safety standards through continuous improvement
YOU MAY BE A GOOD FIT IF YOU HAVE

  • 2 to 4 years of hands-on experience building and deploying ML models in production environments
  • Strong proficiency in Python and deep learning frameworks such as PyTorch or TensorFlow
  • Experience with NLP, large language models, or multi-agent system architectures
  • Rigorous approach to model evaluation: you understand calibration, confidence scoring, and what it means for a model to be trustworthy in a high-stakes domain
  • Familiarity with safety-critical system design including fallback mechanisms, human-in-the-loop controls, and output auditing
  • Comfort with healthcare data standards such as FHIR R4, HL7, or clinical coding systems such as ICD-10 and SNOMED is a meaningful advantage
  • Strong written communication: you can document model behavior, limitations, and validation methodology clearly for clinical and regulatory audiences

PREFERRED QUALIFICATIONS
  • Experience working with clinical AI, medical NLP, or healthcare machine learning systems
  • Knowledge of clinical guidelines, evidence-based medicine frameworks, or drug interaction databases
  • Experience with HIPAA-compliant data handling and privacy-preserving ML techniques
  • Familiarity with multi-agent AI architectures and agentic reasoning systems
  • Experience with AI safety evaluation methodologies including red-teaming and adversarial testing
  • Bachelor's or Master's degree in Computer Science, Biomedical Engineering, Machine Learning, or a related field

COMPENSATION & BENEFITS
  • Salary: Competitive base, negotiable based on experience
  • Performance-based commission structure: your earnings scale directly with your results
  • Two annual festive bonuses, each equivalent to half a month's salary
  • Two-day weekends, 10 days casual leave, 10 days sick leave, and 14 public holidays per CloudlyIO's global holiday calendar for Bangladesh
  • Fully subsidized lunch and evening snacks, plus tea and coffee throughout the day
  • Direct collaboration with US clients and teams, with real exposure to global enterprise AI deals from day one