AI-First Senior Business Analyst
Ukraine, Kyiv · On-Site Full-Time
Company: Orbox Group
Product: AI-native software digitalizing an existing offline oil & petroleum business
Location: Ukraine, Kyiv - on-site, office in the city centre
Employment: Full-time, permanent
Seniority: Senior
Reports to: Head of Delivery & Product
Works with: Business owners & operations team, Engineering team, Design team, AI agents
Mobilization reservation: Full reservation (deferment) from mobilization for male employees
Languages: Ukrainian - native / fluent; English - Upper-Intermediate+ (B2+)
The role
This is the role that defines what this new product is, why each part of it is worth building and how it is described to the machines that build it.
You will report directly to the Head of Delivery & Product and sit in one team with Orbox - same AI-first delivery machine, same tools, same standards. You will own product from the analysis side: discovery, process analysis, PRDs and agent-ready specifications.
This is a hands-on, 0 → 1 analytical role. You will dig into where the work happens. You will map as-is workflows, find where time, money leak and design the to-be processes where AI agents and software do the routine work and people make the decisions.
We operate in a fast-moving startup environment where speed and precision both matter. You must be opinionated about which analysis and documentation tasks AI does well today, which it does not and where in a traditional business AI creates real value versus where it is just noise.
What you will own & do
AI-First Way of Working
• Daily, deep, native use of AI tools for interview and field-note synthesis, process mapping, document analysis, PRD and spec drafting, competitor teardowns and data analysis.
• Treat AI tools the way an engineer treats their IDE: opinionated, tuned, integrated into every step of your workflow.
• Co-design the boundary between what you produce by hand and what is generated, transformed or validated by agents.
• Contribute to internal evals from the analysis side: define what “good” looks like for AI-generated artifacts and for the product's user-facing AI features.
Business Discovery & Process Analysis
• Own end-to-end discovery of the existing business: stakeholder and staff interviews, shadowing, field visits, document and data audits across departments.
• Map as-is workflows (BPMN or similar) and design to-be processes - roles, handoffs, documents, approvals, exceptions and the data behind each step.
• Find and size the opportunities: manual work, errors, delays, fuel and cash losses, reporting pain - and where AI agents can take over routine work (document processing, reconciliation, dispatch, forecasting, anomaly detection).
• Understand the regulatory and accounting side of the business (excise, fiscalization, tax and fuel reporting, primary documents) well enough to turn it into requirements.
• Evidence over opinion: maintain a living research repository so every product decision traces back to a real workflow, a real number or a real user.
PRDs & Specs for the AI-First Delivery Machine
• Own the PRD & spec layer for the product: vision, scope, modules, user stories, acceptance criteria, edge cases, data contracts and state behaviour.
• Convert validated requirements into clear, structured, machine-readable specifications our orchestrator and coding agents can implement, test and evolve reliably.
• Define the domain model: products, tanks and depots, vehicles and routes, counterparties, contracts, prices, documents - the single source of truth for engineering, QA and evals.
• Keep specs in sync with reality: when the business or product changes, the spec changes first.
Delivery, Rollout & Adoption
• Shape the roadmap and scope with the Head of Delivery & Product and business owners - what we digitalize first and why.
• Plan integrations and migration from existing tools and legacy systems (Excel, accounting
