In a world of disruption, unpredictability, and increased expectations, companies need constant awareness of their supply chain exposure and opportunities to adapt. Traditional enterprise-centric processes leverage predominantly internal data that leads to limited visibility insights, and a reactive mode for planning and execution. Companies need to understand real-time signals from across their supply chain ecosystem and rapidly respond in a result-driven, meaningful way. ParkourSC was founded with a vision to unlock the value trapped within supply chains by synthesizing enterprise, network, and contextual data around the flow of products and assets, creating actionable insights to propel enterprise performance.
At its core, ParkourSC provides a cloud-native platform to enable digitally connected supply chains. This yields real-time visibility and intelligence to address supply chain volatility, risk, and compliance down to the product level. Having raised a Series B1 round in 2021, ParkourSC is looking to launch its 2.0 Platform in Q1 ’22 with a significant growth in customers and revenue in the coming years.
ParkourSC is seeking a passionate data scientist with industry expertise to join our growing data analytics & machine learning intelligence team. You will assist in interpreting the requirements of various Big Data analytics use cases and scenarios and drive the ML design and deliver cloud native scalable implementations of machine learning models to drive better predictive intelligence within our platforms from a combination of external and internal data assets. You would be designing predictive recommendations, and decision engines for logistics tracking & optimizations in real time for assets in transit.
The ideal candidate has a proven track record in successfully delivering robust machine learning solutions using cloud-native technologies, with demonstrable experience in building scalable data algorithms with time series data. You will be familiar with enterprise software, cloud technology, SaaS, IoT and big data as they come together to form solutions to meet the biggest problems of customers, such as the digital supply chain. You’ll thrive in a fast-paced environment and can make quick decisions. You love to build with data-pipelines & algorithms. You’re a technologist.
Key Responsibilities & Deliverables
- Design data-driven algorithms to infer key transportation metrics from various data sources, both ParkourSC’s own data and third-party data services.
- Contribute as a lead developer to our ML system architecture, batch & streaming data pipelines, algorithms, and machine learning techniques to build our ML intelligence tools.
- Leverage a big-data delta-lake environment to integrate the MLOPs feature stores as delta lake and maintain feature pipelines.
- Research & implement fast proof-of-technology data strategies from simple SQL-driven methods to advanced ML algorithms as appropriately needed based on the task-complexity.
- Productionize the data science models at scale through a Service Oriented Architecture (SOA) by adopting modern DevOps (CICD), and continuous training (CT) principles.
- Develops and maintains data & ML engineering best practices.
- Develop and maintain a deep understanding of our data & ML platform features and functionality and client-facing products including our underlying data models, transportation metrics, business rules validations, data-visualizations and internal APIs, and their business interpretations to client use-cases.
- Collaborate with our product managers & engineering teams to turn high-level product specifications into clean, accurate analytics and collaborate to convey them via mock-ups, exploratory data-visualizations.
Desired Skills & Experience
- Critical thinking mind who likes to solve complex problems, loves programming, and cherishes to work in a fast-paced environment.
- Minimum of 5+ years of experience in data engineering or data science domain
- Strong hands on Python Programming and SQL skills.
- Experience in analyzing big data and identifying appropriate ML algorithms for predictive analytics .
- Experience with one or more of the following: Time-series analytics, Un-supervised classification, LSTM/RNN models.
- Comfortable with “big-data” analysis tools like spark is a plus.
- Preferably, familiarity with MLOps concepts & tools (Mlflow/DBT/etc.) is a plus.
- Familiarity with workflow management systems like Airflow is a plus .
- Experience with cloud environments such as Databricks/AWS is a plus.
- Preferably Ability to work cross functionally across an organization.
- Excellent organizational skills and demonstrated ability to meet deadlines.
- Proven experience communicating with all levels of management.
- Bachelors in math, engineering, computer science, or related technical field, or equivalent practical experience