Job Description
Our client is a forward-thinking investment firm based in Dubai, UAE, specializing in commercial enterprises and management. They focus on identifying and supporting high-potential businesses, providing strategic investment, and offering expert management services to drive growth and long-term success.
We are currently hiring a
Backend Engineer — AI-Driven Development
for our client who will Own the engineering quality of an AI-driven development team, building a new CTRM (Commodity Trading \& Risk Management) platform for a physical oil-products trader, covering the full deal lifecycle from contract to settlement — pricing against market formulas, cost aggregation, invoicing, logistics, inventory and hedging. In a model where most code is written by coding agents (Claude Code), the engineer is responsible for everything that determines whether that code is correct: architecture, service boundaries, specifications precise enough to implement without guesswork, and review of every line those ships. This is a role for an engineer who already works AI-first — not for vibe coders.
Key Responsibilities:
- Design services, data models, APIs and transactional boundaries from specified requirements.
- Translate requirements into agent-executable task briefs — small enough to verify, large enough to be worth delegating.
- Own and evolve the project’s agent context: CLAUDE.md, coding conventions, architectural guardrails and test policy.
- Review every diff seriously: data model, transaction and concurrency semantics, error handling, migrations, security and performance.
- Write and maintain tests that pin real behaviour — especially around money, rounding, dates and state machines.
- Refactor aggressively when generated code is correct in isolation but wrong for the system.
- Act as reviewer of record for everything you ship, regardless of who or what produced it.
- Ship in two-week sprints against a defined Definition of Ready and Definition of Done
Requirements:
*
AI-driven development is your actual workflow — not a side experiment, not IDE autocomplete.
- A track record of shipping meaningful production features by directing coding agents, with the ability to explain in detail how you structure context, decompose tasks, control cost and verify output.
- Able to read, debug and reason about code you did not write — quickly, in an unfamiliar codebase.
- Willingness to engage with complex financial and logistics logic instead of routing around it.
Qualifications:
- Strong grounding in domain modelling, relational data design and transaction/consistency semantics.
- Solid command of idempotency, concurrency, API design, testing strategy and refactoring discipline.
- Able to explain why a rule exists, not just that a linter enforces it.
Work Experience:
- 7+ years building and operating production backend systems.
- Demonstrated experience delivering production features through AI-driven development / directing coding agents.
Technical Skills:
- Strong Node.js and/or Python.
- Solid SQL (Postgres).
- Comfortable with Docker and CI/CD.
- Strong Git and code-review habits.
- Familiarity with agent tooling and context engineering (e.g. CLAUDE.md, agent task briefs).