Offer summary

Qualifications:

12 years of experience in Machine Learning and AI, with strong expertise in both supervised and unsupervised learning., Proficiency in Python, TensorFlow, SQL, and Jupyter Notebooks is essential., Deep understanding of time-series modeling, anomaly detection, and risk analytics is required., Experience with big data processing and financial data pipelines, along with cloud deployment capabilities..

Key responsabilities:

Set up and configure data pipelines for large-scale data ingestion and processing in cloud environments.

Develop and optimize machine learning models for exception classification and missing value imputation.

Build frameworks for model surveillance and early warning signals to detect anomalies in financial data.

Implement data quality control mechanisms to ensure high-quality data processing and model outputs.

Job description

Job Title: Principal Machine Learning Engineer
Location: Remote
Tech Stack: Machine Learning & AI

About Us:
At Puzzle, we are dedicated to building cutting-edge solutions for our clients. We specialize in delivering scalable, cloud-based applications and data solutions that empower businesses to innovate and grow. As a Lead Software Developer, you will play a critical role in architecting, developing, and leading teams to implement solutions that make a difference.

Job Summary:
The Principal Machine Learning Engineer will be working on the Model Development as a Service (MDaaS) initiative, which focuses on scaling machine learning techniques for exception classification, early warning signals, data quality control, model surveillance, and missing value imputation. The project involves applying advanced ML techniques to large datasets and integrating them into financial analytics systems.

Key Responsibilities

Set up Data Pipelines: Configure storage in cloud-based compute environments and repositories for large-scale data ingestion and processing.
Develop and Optimize Machine Learning Models:
- Implement Machine Learning for Exception Classification (MLEC) to classify financial exceptions.
- Conduct Missing Value Imputation using statistical and ML-based techniques.
- Develop Early Warning Signals for detecting anomalies in multi-variate/univariate time-series financial data.
- Build Model Surveillance frameworks to monitor financial models.
- Apply Unsupervised Clustering techniques for market segmentation in securities lending.
- Develop Advanced Data Quality Control frameworks using TensorFlow-based validation techniques.
Experimentation & Validation:
- Evaluate ML algorithms using cross-validation and performance metrics.
- Implement data science best practices and document findings.
Data Quality and Governance:
- Develop QC mechanisms to ensure high-quality data processing and model outputs.

Required Skillset

12 years of experience in Machine Learning
Strong expertise in AI (Supervised & Unsupervised Learning).
Proficiency in Python, TensorFlow, SQL, and Jupyter Notebooks.
Deep understanding of time-series modeling, anomaly detection, and risk analytics.
Experience with big data processing and financial data pipelines.
Ability to deploy scalable ML models in a cloud environment.

Deliverables & Timeline

Machine Learning for Exception Classification (MLEC): Working codes & documentation
Missing Value Imputation: Implementation & validation reports
Early Warning Signals: Data onboarding & anomaly detection models
Model Surveillance: Fully documented monitoring framework
Securities Lending: Clustering algorithms for financial markets
Advanced-Data QC: Development of a general-purpose QC library

Preferred Qualifications