Data Analyst

Portcast is a venture-backed, Singapore-based logistics technology startup building a real-time transportation visibility platform for global supply chains. We help shippers, manufacturers, and logistics service providers turn data into decisions and decisions into measurable business impact.

Our platform goes beyond visibility. Portcast enables action at scale by surfacing the right risks early, helping teams prevent detention and demurrage, accelerate exception management, and close invoices faster with built-in evidence. We turn visibility into outcomes: reduced costs, improved operational control, and more predictable supply chains.

Founded in 2018 and backed by leading technology investors, we are building for an industry at a critical inflection point of digital transformation. Our team of software engineers, data scientists, and logistics experts is on a mission to make supply chains not just visible, but decisively actionable: end to end.

ABOUT THE ROLE:

Portcast has already been used by global freight forwarding companies, manufacturers and cargo airlines. Our customers trust us to deliver fast, reliable and secure predictions, our engine answers when, where, why, and by how many days a container will be delayed. That trust lives or dies on data quality, and that's what you'll own.

As our Data Analyst, you will be reporting directly to our Analytics Manager and work closely with our Data Science, Engineering, Product, and Commercial teams. You'll sit on a data-heavy product that gives customers end-to-end visibility of their cargo across the ocean journey, making sure the data we ingest into the models and share with customers is error-free and of the highest quality. You won't just run the query and close the ticket here. When an anomaly shows up, you'll chase why it's there, trace it to the real source, and fix the process so it doesn't come back. Curiosity isn't a nice-to-have on this team, it's how we build.

WHAT YOU'LL OWN:

• Documentation, reporting, and root-cause analysis of prediction issues: owning the problem end to end, not just flagging it.

• Analyze ingested and system-generated data for anomalies and gaps, and refer to various data sources to plug those gaps.

• Turn data into stories: surface the pattern behind an issue, propose the fix (QA process-flow change and/or automation), and own the subsequent plan and execution.

• Automate performance/accuracy review processes, report generation, and data visualization using Python and SQL: building reusable, scalable workflows, not one-off scripts.

• Support Engineering and Data Science on system-level data fixes. Understand how the engine makes predictions, and explore improvements by fixing or introducing new data and features.