Jobs at RightShip

Build and evaluate LLM applications, agentic systems, and retrieval pipelines over maritime data. Partner with product managers to prototype AI solutions, define success criteria, design architectures, create evaluation suites, and produce production-ready code. Develop embedding and retrieval pipelines, apply responsible AI practices, document solutions, support engineering handoffs, and advise stakeholders on AI opportunities, trade-offs, and adoption of emerging models and frameworks.

Lead and improve RightShip’s cybersecurity roadmap across cloud, infrastructure, applications, identity, networks, and data. Manage risk registers, vulnerability remediation, penetration testing, incident response, security automation, access governance, compliance frameworks, and resilience planning. Partner with engineering and business stakeholders to embed secure practices, translate technical risk for leadership, and implement sustainable controls. The role requires broad hands-on security expertise, independent judgment, and experience across application and infrastructure security.

Implement and maintain Playwright UI test automation (TypeScript/JavaScript), integrate tests into CI (GitHub Actions/Jenkins), support manual regression/UAT, contribute to load testing, and serve as Scrum Master to facilitate ceremonies, remove impediments, and manage Jira-driven sprint and release activities.

Architect and build production agentic AI systems and the internal developer platform that integrates agent workflows across the SDLC. Design, operate, and evaluate multi-step agent pipelines, develop AI-powered tools in Python, onboard orchestration frameworks, manage AI cost/quality, and enable squads with best-practice guardrails and tooling.

Lead and evolve QA processes; design and execute test plans, cases and regressions; troubleshoot and report defects using JIRA; test APIs with Postman; support UAT; collaborate with Product, QA and dev teams; potentially perform Scrum Master duties (10-20% of workload).