Sr. Modeller / statistician- Brisbane, CA

Hi Jobseekers, this is Nehal from KCS Inc. Milpitas, CA. We are a cloud & data solution providing company currently looking for Looking for someone who has done business (not consumer) credit risk modeling, fraud analytics, survey analytics. If you are excited about working for this role, then please look at the below JD & apply to this job, I would love to have detailed discussion with you.

• Work on Balance Sheet Analytic & Modeling Open Source Action Project to develop, maintain and convert the Residential Retail CCAR/CECL models from production SAS developed models to open source language model via Python/Spark.
• Develop and maintain models and model infrastructure for stress testing (CCAR/DFAST) and reserves(CECL) that support the retail business including Credit Card, Private / Federal Student Loan, Mortgage Loan, etc
• § Work closely with model owner and line of business to integrate model coding standard and program profiling, and compare SAS/Python model, improve Python model’s performance
• § Implement data validation process and testing strategies to address the quality of model runs, model logging and output
• § Join peer’s code review for Residential/No-Residential models (eg. Commercial Residential Model and Pre-Provision Net Revenue PPNR model) and provide review recommendations
• § Commit and communicate the project status via Bitbuck(git), confluence page and JIRA
• Work in three Line of Business (Consumer and Community Banking, Corporate Technology, and Centralized Transaction Operation) as Data Architecture, Application Developer and data Scientist
• Lead data analytical support to provide insight for designing logistic of cash management for firm-wide branches and ATM
• Lead/support the model development (Chase new ATM scheduling model, Enterprise Cash Management Systems Vault Models) by applying predictive models and time series forecasting modeling skill
• Lead model performance validation, including assessment of model conceptual soundness, evaluation of data and assumptions, analysis of model performance, and monitor model consistency
• Collaborate with model governance to generate, deliver and track model governance documentation, which including ( not limited to) the outcomes analysis, back-testing, stress testing and sensitivity analysis. SAS, Python and Bash Shell are applied this implementation.
• Design and develop batch process for the visualization of management information system (MIS) report, analytic summary and ad hoc solution
• Lead the conceptual/ logical/physical design and development of data Oracle warehouse and ETL projects with complexity, cardinality and integrity check and performance tuning
• Migrate applications / database objects / scripts and Control-M batch application from DEV to UAT/PROD environment follow the Software Development Life Cycle (SDLC) and provide run book for operation team
• Apply version control on all the scripts, database objects, and control-m objects via using TortoiseSVN

• Implement data mining, statistical calculation, data import/export via developing and performing parallel computing on high-performance computing (HPC) cluster to locate/characterize human genetic diseases including schizophrenia, bipolar, autism, cleft palate, AITD (autoimmune thyroid disease) for quantitative and computational biology research
• Schedule and optimize batch jobs to execute parallel programming script in the center's cluster as well as in Ohio Supercomputer Center's cluster system
• Provide statistical rationale of missingness ratio, p-value, likelihood ratio of genetics: family relationship and looping, Mendel error, gender error, and clustering using Python and UNIX Bash shell script
• Design data warehouse model (conceptual/logical/physical), build database objectives (schema, table, index, view, and trigger, etc), as well as implement data import/export/dump process to MySQL data warehouse