Responsibilities
- Collaborate with the product and data science teams to build our cashflow data platform, powering our verification of income and cashflow underwriting solutions.
- Collaborate with the data science team to productionalize research models; this may include supplementing research-driven models with additional considerations such as unit processing efficiency, batch efficiency, and parallel computing use cases.
- Increase data observability for customers and stakeholders
- Develop quality controls around our ML-powered services to ensure model effectiveness
- Maintain and improve production ML models such as algorithmic calculations, regression models, and classifiers.
- Develop tooling and frameworks to improve research velocity and outcomes
- Participate in standard engineering activities like technical design, code reviews, on‑call support, documentation, and sprint ceremonies.
Requirements
- 5+ years of software engineering experience
- 2+ years driving large multi‑team software projects from problem statement to ongoing maintenance
- 3+ years experience with databases, data warehouses, or data lakes; strong SQL skills
- 2+ years using data engineering tools like Spark, Hadoop, Pandas, or Airflow
- Proficient in Python; experience writing idiomatic (Pythonic) code
- Experience building Python‑based web applications (Flask, FastAPI, Django)
- Deep understanding of a popular distributed computing framework like Spark, Databricks, Ray, Airflow, Sagemaker, or AWS Batch
- Knowledge of numerical libraries (numpy, pandas, SciPy, et. c)
- Experience in observability tools like Grafana, Kibana, or Datadog
- Ability to design sound, highly performant solutions in AWS; articulate design decisions and tradeoffs
- Firm grasp of software testing methodologies
- Curious, self‑driven, and eager to learn
Sample Projects
- Build a unified data platform capable of seamlessly processing financial data payloads like bank accounts/transactions, payroll information, or OCR‑driven financial document extractions.
- Design an event‑based system for monitoring production ML models
- Create an operations dashboard that articulates the customers and stakeholders
- Stand up an MLOps platform to test model changes against historical data
- Pair with data scientists to write state‑of‑the‑art quantitative cashflow models using computing frameworks like PySpark, Dask, Ray, or Polars.
- Optimize data pipeline latency to shorten overall response time
You Should Especially Apply If
- You want to make a significant impact on your next company
- Going the extra mile to execute well is the norm for you
- You're quick to take the lead when conversations and projects require refinement
- You've been exposed to MLOps (e.g., MLflow, Sagemaker, Databricks)
- You have experience with banking data or working within a FinTech
$193,500 - $236,500 a year
The base salary range is for U.S.-based candidates and is dependent on individual experience, skills, education, location, and qualifications.
We consider all elements of compensation as a part of the value we provide to Novans. This may include base salary, equity grants, incentive compensation for eligible roles, professional development, flexible PTO, and tenure rewards. We offer U.S.-based Novans competitive, employer‑subsidized medical, dental, and vision plans, in addition to mental health and wellness benefits and a range of other benefits & perks.
#J-18808-Ljbffr