SENIOR AI PLATFORM ENGINEER

Duncan & Ross Consulting; Abu Dhabi; On-site; AED 260,000 - 420,000; Full time

Job summary

Duncan & Ross Consulting is seeking a Senior AI Platform Engineer to architect and evolve reusable AI platform capabilities for building and deploying AI agents and LLM-powered services. The role focuses on production-grade reliability, security, and observability across cross-functional teams in Abu Dhabi, UAE.

The candidate will own core platform architecture, guide CI/CD, and mentor engineers, with an emphasis on LangChain/LangGraph orchestration, LLM integrations, RAG patterns, and scalable

Job description

Senior AI Platform Engineer

Applied AI | 5-6 years of relevant experience

Role purpose

Architect and evolve the reusable platform capabilities that enable engineering teams to build, deploy, govern, and scale secure, production-grade AI agents and LLM-powered applications.

Job Summary

We are seeking an experienced Senior AI Platform Engineer with 5-6 years of relevant backend, platform, distributed systems, or applied AI engineering experience. The role will own key architectural and technical decisions for the organization's AI platform, building reusable frameworks, orchestration capabilities, model and tool integrations, and operational controls for production-grade AI systems. The successful candidate will work across engineering, architecture, security, and product teams to establish standards and accelerate the delivery of reliable, observable, secure, and scalable AI-powered solutions.

Key Responsibilities

• Design, develop, and evolve the core architecture of the shared AI platform used to build and deploy AI agents and LLM-powered services.
• Architect and implement agent orchestration frameworks using LangChain, LangGraph, or comparable technologies for complex, stateful, and multi-step AI workflows.
• Develop and maintain platform SDKs, Python libraries, templates, APIs, and developer tooling that standardize integration with models, tools, data sources, and enterprise systems.
• Own the LLM integration layer, supporting multiple commercial providers, locally hosted models, embedding services, vector stores, and internal AI services.
• Design platform capabilities for prompt lifecycle and configuration management, tool calling, memory and state handling, agent execution, evaluation, and model routing.
• Implement observability, tracing, and evaluation capabilities using Langfuse or equivalent platforms to monitor prompts, agent execution, latency, quality, token usage, cost, and system performance.
• Architect retrieval-augmented generation (RAG) capabilities, including ingestion, indexing, retrieval, reranking, grounding, and evaluation patterns.
• Ensure the platform meets production requirements for scalability, availability, resilience, security, privacy, and performance through sound engineering and operational practices.
• Partner with Applied AI Engineers, architects, security teams, and product owners to define reusable patterns, development standards, and platform guardrails.
• Lead technical design reviews, influence the platform roadmap, maintain architectural documentation, and drive automated testing, CI/CD, and release quality.
• Mentor junior engineers, provide technical guidance, and promote engineering excellence across the AI platform team.

Required Skills and Qualifications

• 5-6 years of relevant experience in backend engineering, platform engineering, distributed systems, or applied AI development.
• Advanced Python programming skills, including experience building platform frameworks, SDKs, APIs, and reusable packages.
• Hands-on experience designing and building LLM-powered platforms, AI infrastructure, agent-based systems, or production generative AI services.
• Strong practical experience with LangChain, LangGraph, or similar agent and workflow orchestration frameworks.
• Deep understanding of prompt engineering, RAG architectures, embeddings, retrieval and reranking, tool integration, memory, and agent workflows.
• Proven experience designing microservices, asynchronous processing patterns, APIs, and scalable distributed systems.
• Strong command of software engineering practices, including design patterns, automated testing, code review, CI/CD, and containerization.
• Strong understanding of logging, monitoring, distributed tracing, evaluation, and performance management for AI systems.
• Bachelor's degree in Computer Science, Software Engineering, Artificial Intelligence, or a related discipline, or equivalent practical experience.

Preferred Qualifications

• Experience designing vector database, semantic search, and enterprise retrieval pipelines.
• Experience implementing AI observability and evaluation using Langfuse, LangSmith, or equivalent tools.
• Experience integrating multiple LLM providers and self-hosted or open-source models, including routing and fallback patterns.
• Experience building internal AI platforms, reusable Python frameworks, or developer tooling used by multiple engineering teams.
• Experience with Docker, Kubernetes, cloud-native architectures, infrastructure automation, and secure secrets and API management.
• Knowledge of responsible AI, model governance, data privacy, access control, and enterprise security requirements.

Key Competencies

• System design: Translates complex requirements into coherent, scalable, and maintainable platform architectures.
• Platform thinking: Builds reusable capabilities, paved roads, and standards that improve engineering productivity.
• Technical leadership: Leads design decisions, mentors engineers, and raises engineering standards through influence and example.
• Ownership and reliability: Owns production readiness, resilience, maintainability, and continuous improvement.
• Collaboration and communication: Communicates architectural decisions clearly and aligns stakeholders across engineering, product, security, and operations.

Location: Abu Dhabi, UAE (on-site) | Duration: 3 months | Start: ASAP, subject to security clearance | Language: Arabic speakers preferred

Vertical

Technology