About the job
Join a leading client of Weekday as a Lead Machine Learning Engineer!
With a minimum of 5 years of experience, your expertise will drive the design, development, deployment, and operation of cutting-edge AI systems in the cyber security domain. You will play a pivotal role in technical leadership, hands-on model development, and system integration across various functions.
Your responsibilities will include owning multiple production ML models focused on threat detection, ensuring their performance, reliability, and scalability, while also mentoring engineers to foster technical excellence.
Key Responsibilities
1. Technical Leadership & Architecture
- Design and manage the machine learning architecture for threat detection platforms.
- Establish model development standards, deployment patterns, and quality benchmarks.
- Make informed decisions regarding model selection, scalability, and cost considerations.
- Conduct comprehensive code and model evaluations for enterprise-level reliability.
- Mentor machine learning engineers to enhance team capabilities.
2. Model Development & Lifecycle Management
- Develop and deploy various production machine learning models including phishing detection, SMS scam detection, call fraud detection, and behavioral anomaly detection.
- Oversee the entire machine learning lifecycle from data ingestion to model monitoring.
- Utilize advanced techniques such as ensemble learning, deep learning, and transfer learning.
- Optimize models for accuracy, latency, and operational effectiveness.
3. ML Infrastructure & Deployment
- Build and maintain production-quality ML pipelines.
- Develop model-serving APIs using FastAPI or Flask.
- Containerize applications with Docker and Kubernetes.
- Implement CI/CD pipelines for ML workflows.
- Collaborate with backend and cloud infrastructure teams for seamless integration.
4. Monitoring, Observability & Explainability
- Design and implement model monitoring and alerting mechanisms.
- Utilize tools such as Prometheus and Grafana for performance tracking.
- Ensure model explainability using techniques like SHAP and LIME.
5. Data Engineering & Workflow Orchestration
- Facilitate the orchestration of workflows for data processing and model deployment.