AI Engineer

One Way Ventures; Dubai; On-site; AED 350,000 - 700,000; Full time

Job summary

Qashio is seeking an AI engineer to translate cutting-edge AI into reliable software. You will own architecture for AI/LLM systems end to end, build reusable platform components and implement security controls for SSO/RBAC, data isolation and auditing.

You will partner with product to ship high-quality, guardrails-enabled solutions while keeping the tech modular and vendor-neutral for long-term flexibility and reliability.

Qualifications

• 5+ years software engineering with strong Python and production backend/API ownership.
• Hands-on with LangChain/LangGraph, OpenAI Agents SDK, Microsoft Agent Framework/Semantic Kernel incl. durable workflows.
• Experience building permission-aware RAG and ingestion pipelines with LlamaIndex, Haystack or LangChain and vector stores (pgvector, Pinecone, Qdrant).
• Cloud-native fundamentals plus evaluation and tracing with LangSmith, Arize Phoenix, DeepEval or equivalent and CI/CD release gates.
• Guardrails experience with NVIDIA NeMo Guardrails, Guardrails AI or OpenAI Guardrails, covering PII/data leakage and safe tool usage.
• Fine-grained permissions and secure tools/connectors with OPA/OpenFGA, MCP/OAuth, least-privilege scopes and approvals.
• Clear communicator who translates ambiguity into milestones, architecture decisions and reliable software.

Responsibilities

• Own the technical architecture of our AI/LLM systems end to end from framework choices to deployment.
• Build reusable platform components: a model gateway, permission-aware RAG, agent orchestration and secure connectors.
• Translate security policy into technical controls for SSO/RBAC, data classification and isolation, PII, secrets and audits.
• Establish evaluation, observability and release gates for quality, safety, cost, latency and drift.
• Partner with product and business teams to ship dependable solutions with proper human oversight.
• Keep architecture modular and vendor-neutral, avoiding lock-in to a single framework or provider.

Skills

Python

APIs / Backend ownership

LangChain / LangGraph

OpenAI Agents SDK

MCP connectors / tool orchestration

Security & compliance mindset

Tools

LangChain

LangGraph

OpenAI Agents SDK

Microsoft Semantic Kernel

Haystack

pgvector / Pinecone / Qdrant

NVIDIA NeMo Guardrails

OpenAI Guardrails

OPA / OpenFGA

MCP / OAuth

Job description

Role Overview

At Qashio, we're transforming how businesses manage company spending. We are looking for an AI engineer who turns cutting-edge AI into software people can rely on. You care about quality, safety and doing things properly, and you are happiest owning a hard problem from first design to something running in production.

Responsibilities

• Own the technical architecture of our AI / LLM systems end to end - from framework and tooling choices through to deployment.


• Build reusable platform components: a model gateway, permission-aware RAG, agent orchestration, secure tools/MCP connectors and internal-system integrations.


• Translate security and compliance policy into technical controls for SSO/RBAC, data classification and isolation, PII, secrets, approvals and audit.


• Establish evaluation, observability and release gates covering answer and retrieval quality, safety, cost, latency, reliability and drift.


• Partner with product and business teams to turn priority problems into shipped, dependable solutions, with the right human oversight.


• Keep the architecture modular and vendor-neutral, so we are never locked to a single framework or model provider.

Qualifications and Experience

• 5+ years software engineering, with strong Python and production backend/API experience and ownership of 0-to-1 systems.


• Hands-on production experience with LangChain/LangGraph, OpenAI Agents SDK, Microsoft Agent Framework/Semantic Kernel or comparable agent SDKs, including durable workflows, structured outputs, tool calling and HITL.


• Experience building permission-aware RAG and ingestion pipelines with LlamaIndex, Haystack or LangChain and vector stores such as pgvector, Pinecone or Qdrant, including source ACLs and data isolation.


• Strong cloud-native engineering fundamentals, plus evaluation and tracing with LangSmith, Arize Phoenix, DeepEval, Ragas or equivalent, including CI/CD release gates and incident readiness.


• Hands-on experience implementing guardrails with NVIDIA NeMo Guardrails, Guardrails AI, OpenAI Guardrails or equivalent, covering prompt injection, PII/data leakage, output validation and unsafe tool use.


• Experience implementing fine-grained permissions and secure tools/connectors with OPA, OpenFGA, Cedar or equivalent, plus MCP, OAuth/service authentication, least-privilege scopes and approval gates.


• Clear communicator who turns ambiguous problems into scoped milestones, architecture decisions, runbooks and shipped, reliable software.

Nice-to-have

• Experience handling sensitive data in fintech, banking or another regulated environment (GDPR, data residency, SOC 2 and/or PCI).


• Experience with model gateways, multi-provider routing, LLM cost controls and tracing/evaluation platforms.


• Working knowledge of TypeScript/React, internal developer platforms or multi-tenant SaaS.