Lead ML engineer

Project Description

A digital health company focused on revolutionizing the pharmacy regulatory market through data-driven innovation and technology. The platform leverages AI/ML to accelerate the approval process of therapeutic products, automate regulatory workflows, and enhance decision intelligence for compliance teams.

Role Overview

We are seeking a highly skilled Lead Machine Learning Engineer to join our cross-functional AI team. You will be responsible for designing, training, and deploying machine learning models that power intelligent automation and decision-support systems across our SaaS platform. This role bridges data science, software engineering, and infrastructure — ensuring that models move from prototype to scalable production systems efficiently and reliably.
 

Key Responsibilities

Model Development & Optimization

• Design, build, and train ML models for classification, NLP, entity extraction, and prediction tasks using modern frameworks (e.g., PyTorch, TensorFlow, scikit-learn).
• Conduct feature engineering, hyperparameter tuning, and model validation using statistical and ML techniques.
• Implement retraining, versioning, and A/B testing strategies to continuously improve model performance.
   

MLOps & Deployment

• Collaborate with DevOps and backend engineers to containerize, deploy, and monitor models in production environments.
• Develop automated data pipelines for training, validation, and inference (Airflow, Kubeflow, MLflow).
• Ensure reproducibility, observability, and CI/CD integration of ML workflows using best practices in MLOps.
   

Data Engineering & Experimentation

• Partner with data engineers to define data ingestion and preprocessing strategies for structured and unstructured datasets.
• Build scalable experimentation frameworks and maintain benchmark datasets for consistent model evaluation.
• Establish and maintain data quality checks, drift detection, and feedback loops from production systems.
   

Collaboration & Impact

• Work closely with product and domain experts to translate business problems into ML tasks with measurable ROI.
• Participate in technical design reviews, code reviews, and cross-functional sprint planning.
• Document methodologies, experiments, and model cards for transparency and compliance (HIPAA, SOC 2, GxP).

Requirements

Experience

• 5+ years of hands-on experience in developing, deploying, and maintaining ML models in production environments.
• Demonstrated success in applying ML/NLP to real-world business problems (healthcare, fintech, or regulated industries preferred).

Technical Skills

• Strong proficiency in Python and core ML/data libraries (NumPy, Pandas, scikit-learn, PyTorch/TensorFlow).
• Experience building and optimizing data pipelines using tools like Airflow, Spark, or Ray.
• Solid understanding of software engineering principles, APIs, and containerization (Docker, Kubernetes).
• Familiarity with cloud services (AWS SageMaker, GCP Vertex AI, or Azure ML).
• Experience with ML lifecycle management tools (MLflow, DVC, Weights & Biases).
• Understanding of data security, governance, and compliance in regulated domains.
   

Soft Skills

• Strong analytical and problem-solving skills with attention to detail.
• Excellent communication skills; able to explain technical concepts to non-technical stakeholders.
• Proven ability to work in collaborative, agile environments.
   

Nice to Have

• Experience in NLP (transformers, embeddings, text summarization, entity recognition).
• Exposure to LLM fine-tuning, prompt engineering, or retrieval-augmented generation (RAG).
• Familiarity with healthcare data standards (FHIR, HL7) or claims processing workflows.
• Contributions to open-source ML projects or published research.

What Success Looks Like (First 90 Days)

• Deliver a trained and validated ML model integrated into one production feature.
• Establish an end-to-end retraining pipeline with automated evaluation and version tracking.
• Deploy monitoring and alerting for model drift and performance degradation.
• Contribute to the team’s internal ML standards and reusable templates for experimentation and deployment.