AI Engineer

Rewaa is on a mission to revolutionise retail! Our cutting‑edge SaaS platform empowers retailers to move and grow faster. We provide innovative solutions for point‑of‑sale, inventory management, omnichannel integrations, tax and accounting, and reporting, all delivered on a single screen with our lightning‑fast, robust hardware. With over 10,000+ customers and an ambitious trajectory toward global expansion, there's never been a better time to join Rewaa!

As a Staff AI Engineer, you’ll define and lead the technical direction for production‑grade AI systems across the company. You won’t just build agents—you’ll design the platforms, patterns, and guardrails that other engineers rely on to ship AI safely and at scale.

You’ll architect end‑to‑end AI systems such as customer intelligence agents, internal copilots, automated workflows, and retrieval‑augmented generation (RAG) platforms used by multiple teams. You’ll work with modern frameworks like Lang Graph, Llama Index, AWS Agent Core, or Vertex AI Agent Builder, and make principled decisions about when to use them—and when not to.

This is not a research role.

It’s senior‑level engineering leadership with deep hands‑on ownership. You’ll set standards, review designs, mentor engineers, and still write production code when it matters most. You’ll be accountable for reliability, cost, and long‑term maintainability of AI systems running in production.

• Define reference architectures and best practices for AI systems across teams
• Lead design reviews for complex AI and agentic systems
• Make high‑impact architectural decisions balancing speed, cost, accuracy, and reliability
• Identify when to build vs buy vs integrate third‑party AI tooling

• Design scalable RAG and agent‑based systems (single‑agent and multi‑agent)
• Own system‑level concerns: orchestration, memory, retrieval, evaluation, and fallback strategies
• Establish prompt versioning, evaluation, and deployment standards across the org
• Drive consistency in embeddings, vector databases, and retrieval strategies

• Design resilient systems: retries, timeouts, circuit breakers, graceful degradation
• Build async pipelines, background workers, and event‑driven workflows
• Own production incidents and lead post‑mortems with clear corrective actions

• Define and monitor AI‑specific SLIs/SLOs (latency, accuracy, cost per request, hallucination rate)
• Drive LLM cost optimization strategies at scale
• Implement rollout strategies using feature flags, canaries, and staged deployments
• Ensure security, compliance, and PII protection in AI systems

• Mentor senior and mid‑level engineers in AI systems engineering
• Raise the engineering bar through code reviews, design guidance, and shared tooling
• Partner with product, data, and leadership to shape the AI roadmap
• Turn ambiguous business problems into clear technical plans

• Proven experience designing and operating multiple AI systems in production
• Deep expertise in LLM orchestration frameworks (Lang Graph, Llama Index, AWS Agent Core, or similar)
• Strong understanding of RAG systems: embeddings, chunking strategies, hybrid retrieval, reranking
• Experience treating prompts as production artifacts: versioning, testing, evaluation, rollback

• Advanced Python engineering with strong system design fundamentals
• Experience building distributed, async, and event‑driven systems
• Testing strategies for non‑deterministic systems (prompt tests, golden datasets, eval pipelines)
• Ability to debug complex failures across multiple services and AI components

• Monitoring and observability for AI systems (not just infrastructure)
• Cost modeling and optimization for LLM‑powered workloads
• CI/CD pipelines and safe deployment strategies for AI features
• Security best practices including prompt injection mitigation and data isolation
• 6–10+ years of professional software engineering experience
• 3+ years building and operating AI‑powered systems in production environments

• You’ve designed a shared RAG or…