Simpl - Data Scientist - Machine Learning/Deep Learning (5-7 yrs)

About Simpl :

Simpl is revolutionizing how people interact with money.

We're tackling complex problems in the fintech space, and we need talented and passionate individuals to join our team.

We're building a supportive and collaborative environment where smart people can thrive, with a focus on autonomy, impactful work, and personal growth.

If you're driven to solve challenging problems and make a real difference, we encourage you to apply.

About the Role :

As a Data Scientist at Simpl, you will be a key contributor in developing data-driven solutions that directly impact our core business functions, including underwriting, anti-fraud, retention, and collections.

You will work closely with cross-functional teams, leveraging your expertise in machine learning (ML), deep learning (DL), and potentially reinforcement learning (RL) to analyze large datasets, build sophisticated models, and deploy scalable solutions.

This role offers an exciting opportunity to work on high-impact projects and further develop your skills in a fast-paced, high-performance environment.

Responsibilities :

- Own and lead data science projects from inception to completion, including defining problem statements, formulating hypotheses, designing experiments, and presenting results to stakeholders.

- Collaborate with product managers and business stakeholders to understand business needs and translate them into actionable data science projects.

- Prioritize and manage multiple projects concurrently, ensuring timely delivery and high-quality results.

- Design, develop, and implement advanced machine learning models, including :

1. Supervised Learning : Regression (Linear Regression, Ridge/Lasso Regression, Support Vector Regression, Tree-based models like Random Forest, Gradient Boosting Machines (GBM), XGBoost, LightGBM, CatBoost) and Classification (Logistic Regression, Support Vector Machines, Decision Trees, Random Forest, GBMs).

2. Clustering (K-Means, DBSCAN, Hierarchical Clustering), Dimensionality Reduction (PCA, t-SNE), Anomaly Detection.

3. Convolutional Neural Networks (CNNs) for image-related tasks.

4. Recurrent Neural Networks (RNNs), Long Short-Term Memory (LSTM) networks, Gated Recurrent Units (GRUs) for sequence data (time series, text), Transformers for NLP tasks.

- Optimize model performance using techniques like hyperparameter tuning, cross-validation, and feature engineering.

- Evaluate model performance using appropriate metrics and statistical methods.

- Proactively monitor, evaluate, and optimize the performance of deployed models in production.

- Develop and implement model monitoring systems to detect and address model drift and degradation.

- Analyze model performance metrics, identify areas for improvement, and iterate on model development.

- Clearly communicate the business impact of your models to stakeholders through reports, presentations, and dashboards.

- Partner closely with data engineers to deploy and productionize machine learning models using appropriate technologies (Docker, Kubernetes, cloud-based deployment platforms).

- Gain hands-on experience with the entire end-to-end data science pipeline, from data collection and preprocessing to model deployment, monitoring, and maintenance.

- Collaborate with other data scientists and engineers to share knowledge and best practices.-

- Explore and analyze large, complex datasets using tools like Pandas, NumPy, and SQL.

- Identify patterns, trends, and anomalies in data that can inform business decisions.

- Develop data visualizations and reports using libraries like Matplotlib, Seaborn, and Plotly to communicate findings effectively.

- Embrace an experiment-driven approach to problem-solving.

- Design and execute A/B tests and other experiments to evaluate the effectiveness of different approaches.

- Iterate on solutions based on data and feedback.

- Actively participate in Simpl's data science community by sharing knowledge, learning from peers, and contributing to a collaborative and supportive environment.

- Stay up to date with the latest advancements in machine learning, deep learning, and related fields.

Requirements :

- Educational Background : Master's degree in computer science, Data Science, Mathematics, Statistics, or a related field.

- A Ph.is a plus.

- Expert proficiency in Python programming, including extensive experience with data science libraries like Pandas, NumPy, Scikit-learn, TensorFlow, PyTorch, and other relevant libraries.

- Ability to write clean, efficient, and well-documented code.

- Expert proficiency in SQL for querying and manipulating data from relational databases.

- Experience with writing complex SQL queries and stored procedures.

- Machine Learning Expertise : Deep understanding of machine learning and deep learning concepts, including various algorithms, model evaluation metrics, and best practices.

- Strong foundation in statistical concepts and linear algebra.

- Familiarity with cloud platforms like AWS, GCP, or Azure, and experience with using cloud-based machine learning services.

- Experience with big data technologies like Spark, Hadoop, and Hive.

- Familiarity with MLOps principles and tools for deploying and managing machine learning models in production.

- Extensive experience with data preprocessing techniques (data cleaning, feature engineering, feature selection), data validation, and model selection.

- Experience with handling imbalanced datasets and missing data.

- Ability to understand business objectives and translate them into data science problems.

- Ability to align data science solutions with key performance indicators (KPIs).

- Exceptional analytical thinking and problem-solving skills, with the ability to break down complex problems into smaller, manageable tasks.

- Excellent written and verbal communication skills, with the ability to clearly explain technical concepts to both technical and non-technical audiences.

- Ability to create compelling presentations and reports.

Nice to Have :

- Experience with deep learning models (CNNs, RNNs, Transformers), reinforcement learning, or graph-based techniques.

- Familiarity with big data technologies (Spark, Hadoop) and cloud-based ML platforms (AWS SageMaker, Google Cloud AI Platform, Azure Machine Learning).

- Knowledge of real-time decisioning systems and financial risk modeling.

- Prior experience in the fintech or payments industry.

- Contributions to open-source projects, research papers, or data science blogs.