Data Scientist

Candescent•Atlanta, GA

About The Position

Candescent is the leading cloud-based digital banking solutions provider for financial institutions. We are transforming digital banking with intelligent, cloud-powered solutions that connect account opening, digital banking, and branch experiences for financial institutions. Our advanced technology and developer tools enable seamless, differentiated customer journeys that elevate trust, service, and innovation. Success here requires flexibility in a fast-paced environment, a client-first mindset, and a commitment to delivering consistent, reliable results as part of a performance-driven, values-led team. With team members around the world, Candescent is an equal opportunity employer. Candescent is the leading cloud-based digital banking solutions provider for financial institutions. We are transforming digital banking with intelligent, cloud-powered solutions that connect account opening, digital banking, and branch experiences for financial institutions. Our advanced technology and developer tools enable seamless, differentiated customer journeys that elevate trust, service, and innovation. Success here requires flexibility in a fast-paced environment, a client-first mindset, and a commitment to delivering consistent, reliable results as part of a performance-driven, values-led team. With team members around the world, Candescent is an equal opportunity employer. The Data Scientist in Candescent’s Data and AI product organization plays a critical role in driving the data-fueled, AI-first and intelligence-driven digital banking product strategy and vision. The Data Scientist works closely with product management, product design, and engineering teams in the agile execution process. The Data Scientist applies statistical and AI/ML data analysis in every phase of the data & AI product development lifecycle from inceptions to launches, and delivers the analytical datasets, data insights, metrics, models, visualization and dashboards to help drive the product design, development and go-to-market toward the right direction with data-informed decision making and recommendation.

Requirements

Bachelor’s Degree required, preferably in data science, statistics, math, computer science, business analytics, software engineering or equivalent fields; master’s degree preferred
Data analytics skills and experience in SQL, Python, pandas, databases, data warehousing, data lake, and cloud data platforms
Experience in statistical data analysis and modeling: regression, hypothesis testing, time-series analysis, PCA, sampling, and imbalanced data analysis
Knowledge and experience with machine learning methods: logistic regression, decision trees, random forest, gradient boosting, anomaly detection, clustering, error analysis, regularization, supervised and unsupervised learning, and precision and recall tuning
Familiar with AI and Gen AI models and systems: neural network, deep learning, NLP, LLMs, multi-modal models, recommender systems, agentic AI, fine-tuning, and reinforcement learning
Experience with Scikit-learn, TensorFlow, Keras, Pytorch, numpy and other popular AI/ML tools and packages
Advanced skills in data visualization, dashboard development, and data storytelling
Strong communication and presentation skills
Passion for detailed data analysis and natural curiosity to stay current on the latest developments in statistics, machine learning, AI and Gen AI

Responsibilities

Product Analysis : Conduct data set collection, data cleansing, and data analysis with statistical and AI/ML methods to understand product usage, journeys, funnels and product health, and identify product gaps and areas of improvement
User Insight Analysis : Perform user behavioral analysis, discover underlying user profiles and attributes, learn foundational user embeddings, detect user personas, apply effective clustering for user segmentation analysis, and predict user’s next possible digital banking actions
Product Experimentation Analysis : Plan A/B and multi-variate statistical testing, define clear and testable hypotheses with measurable success metrics, design randomized and unbiased sampling strategies, monitor and collect test results, and apply statistical testing to draw conclusions
Product Acceptance Analysis : Utilize statistical and AI/ML techniques to conduct comprehensive data analysis during product acceptance. Evaluate the precision and recall of data and AI product outputs, identify false positives and potential product limitations, uncover patterns of unexpected product behavior and governance issues, and provide recommendations for robust guardrails
Go-to-market Product Analysis : Define the key performance metrics with product management, ensure the KPIs are instrumented in products, collect data from different channels and analytical platforms, perform data analysis and develop dashboards to monitor the post-launch performance, measure user conversion, user engagement and user retention, develop cohort analysis to quantify the long-term benefit of the product launch, and work with sales/marketing to design and fine-tune campaigns to optimize the product usage
Data-driven Customer Engagement : Collaborate with account and relationship team to apply the data-driven approach and methodology to the product integration and product launch with financial institutions, provide data analytical results to justify the product values during the proof-of-concept (PoC) engagement, and deliver data insight and convincing data findings to ensure successful product launch
Data Product Research : Research market and technology trends, analyze what product features can be developed with the latest statistical models, AI/ML models, agentic AI systems, recommender systems, and other deep learning algorithms, prototype intelligence-driven features to demonstrate the viability to the product and engineering teams, conduct competitive data analysis in the market, and justify the new product’s leadership position in the industry with thorough data metrics
Risk and Fraud Analysis : Leverage advanced analytical techniques, such as anomaly detection, decision trees, random forest, neural networks, graph network, supervised and unsupervised AI/ML models, to spot unusual behaviors or transactions. Analyze historical fraud data to identify common fraudulent patterns, evaluate and monitor risk/fraud model performance in real-time with comprehensive metrics (accuracy, precision, recall, F1 score, AUC-ROC, etc.), create decision rules and fine-tune models to adapt to new fraud patterns
Vendor and Partner Analysis : Evaluate product performance from different vendors and partners in data, AI, risk and fraud solutions. Collect unbiased benchmark data sets for vendor’s product evaluation, generate data insights to help select the best-performing partners, and conduct on-going data analysis to ensure the vendor’s solution meets the performance criteria
Data Analytics Visualization and Storytelling: Generate key metrics, charts, graphs, reports, dashboards and drill-downs to communicate the key product message effectively to internal and external stakeholders
Data Quality, Availability and Governance Analysis : Investigate the root cause of data integrity issues, identify missing data, duplicate data, inconsistent data, and other data errors, define standards, processes and pipelines for data cleansing and normalization, and ensure data use aligns with regulations and ethical guidelines.