LeafLink is seeking a proven leader and expert in applied data science to join our New York team. The ideal candidate will possess experience and acumen in understanding business opportunities and challenges in a marketplace ecosystem and applying data science tools to solve them. You enjoy working in greenfield settings, assessing areas ripe for maximum impact, and scoping projects to deliver value. You have built and deployed into production machine learning models. You are comfortable partnering with DevOps and Data Engineers to create ML pipelines. You are well versed in statistical inference methods and analyzing results from A/B and muti-variate tests. You are passionate about keeping up with the trends in the data science space and introducing industry-leading concepts to your peers, manager, and team. You deeply value frequent and detailed communication to foster alignment and cross-functional collaboration to ensure data science solutions are grounded in the full context of the business and align with stakeholder expectations. Above all, you firmly believe that data science applications should drive business value.
What You'll Be Doing- Building the function from the ground up with expertise on how to source, fun, and present experiments to a non-technical crowd.
- Execute analytics and data science project plans and workflows by conducting deep dives into problem sets, recommending solution paths, and implementing them
- Conducting analysis and uncovering insights to drive business decisions
- Build and deploy rapid prototypes as concept demonstrators to business stakeholders and product managers
- Partner with product managers on enabling data-driven features on the platform through the application of advanced analytics and ML
- Develop and deploy ML pipelines using existing infrastructure and tool kits.
- Contribute to a test and learn culture at LeafLink by developing processes for conducting feature experiments and inferring impact on key performance metrics
- Communicate results and business value of experimentation and ML work to a non-technical audience
Experience
- 7+ years of experience using SQL & Python on the job
- Deep understanding of feature engineering on structured and unstructured data
- Proven experience in building ML Pipelines using popular Python-based frameworks such as sklearn, keras, spark mlib, pytorch
- Deep experience with statistical analysis and inference
- Data visualization tools and packages like seaborn, matplotlib, or other BI software are a must-have. Specific expertise in visualizing model results in Sigma is a strong plus.
- Has driven the building and deploying of a different model(s) into the production environment is a must-have
- Previous projects in conducting business analysis and presenting results in structured narratives using presentation tools
- Experience using Airflow to build workflows incorporating feature extraction, running model predictions, and persisting output of model to data stores
- Comfortable using Git to share and manage code
- Enjoys working in a fast-paced growth business with many collaborators
- Has the ability to work across the stack when the need arises
Desired Experience
- Experience with non-linear optimization, critical path simulation, and network analysis is a strong plus
- Working in a SaaS or product-based technology environment working alongside Developers, DevOps, Data Engineers, and Analytics Engineers
- Deploying models in high-velocity streaming data environments using Spark or other frameworks
- Working with at least one ML Ops management platform such as ML Flow, Databricks, AWS SAgemaker, h2o.ai
- Has built a DS function in a prior role