Senior AI Engineer – Generative AI, Agentic Systems

This is a fully remote position, open to applicants in United Arab Emirates (UAE).

📋 Description

• Design and implement Python-based services that connect large language models to enterprise APIs, data sources, and approved tools.

• Construct retrieval-augmented generation systems, which encompass document ingestion, indexing, retrieval, reranking, and source attribution.

• Develop agentic workflows that feature explicit permissions, reliable state management, retries, audit trails, and approval gates for significant actions.

• Create document intelligence pipelines that yield validated structured outputs for downstream applications and ERP workflows.

• Generate evaluation datasets along with release criteria.

• Assess answer quality, identify failure modes, measure latency, and evaluate operating costs.

• Deploy and manage AI applications in customer-controlled cloud or private settings.

• Monitor systems, address incidents, and provide comprehensive handover documentation.

• Collaborate closely with founders and customer engineering teams.

• Take ownership of impactful technical decisions and influence enterprise AI engineering practices.

⛳️ Requirements

• Proven track record of delivering production software and LLM applications, with accountability for architecture, deployment, and operational quality.

• Proficient in Python, API design, and skilled in testing and debugging.

• Hands-on experience with containers, Git, and CI/CD processes.

• Practical experience with retrieval-augmented generation, tool utilization, structured outputs, and evaluation extending beyond mere prompt experimentation.

• Familiarity with Amazon Bedrock, Anthropic Claude, or similar model services.

• Sound judgement in selecting models and deployment strategies tailored to specific use cases.

• Capability to assess data access, manage untrusted inputs, and evaluate agent permissions.

• Ability to articulate trade-offs to customers and guide engineering decisions in English.

• Experience with self-hosted models, GPU infrastructure, vector search, MCP integrations, or agent frameworks is advantageous.

• CV, location, and availability must be included in the application.

• A production AI example detailing contribution, evaluation approach, deployment environment, and an addressed failure mode is required in the application.

• Applications must be submitted through the job portal.

🏝️ Benefits

• 3-month contract.

• 3-month probation period.

• 1 day of annual leave.

• Opportunity to work closely with the founders.

• Ownership of meaningful technical decisions.

• Opportunity to influence how the team builds, evaluates, and operates enterprise AI.

• Collaboration with customer engineering teams.