AI PLATFORM ENGINEER

Duncan & Ross Consulting; Abu Dhabi; On-site; AED 180,000 - 300,000; Full time

Job summary

Duncan & Ross Consulting in Abu Dhabi seeks an AI Platform Engineer to build reusable platform capabilities that enable engineering teams to develop, deploy, operate, and scale secure AI agents and LLM-powered applications.

The role involves implementing agent orchestration workflows with LangChain/LangGraph, building reusable Python libraries, APIs, and tooling to integrate models, tools, data sources, and internal systems, and enhancing observability and performance across production-grade AI

Qualifications

• 2-3 years of backend/platform/APIs or applied AI development experience.
• Strong Python programming skills, including API/service development.
• Experience with LLM-powered apps or agents is a plus.
• Familiarity with LangChain, LangGraph, or similar orchestration frameworks.
• Knowledge of REST, microservices, asynchronous processing, and distributed systems.
• Experience with Git, CI/CD, and containerization.

Responsibilities

• Contribute to design, development, and maintenance of a shared AI platform for AI agents and LLM services.
• Implement agent orchestration workflows using LangChain, LangGraph, or similar frameworks.
• Develop reusable Python libraries, SDKs, templates, and APIs for models, tools, data sources, and internal systems.
• Build integrations with LLMs (local and commercial), embedding models, and vector stores.
• Enhance prompt/configuration management, tool invocation, memory/state handling, and agent execution.
• Incorporate observability and evaluation tools to monitor prompts, latency, token usage, and cost.
• Support retrieval-augmented generation pipelines including document ingestion and indexing.
• Improve reliability, scalability, security, and performance via testing, automation, and best practices.
• Collaborate with Applied AI, product, and platform teams to translate requirements into reusable capabilities.
• Produce documentation and contribute to tests, CI/CD, and releases.

Job description

AI Platform Engineer

Role purpose

Build and enhance the reusable platform capabilities that enable engineering teams to develop, deploy, operate, and scale secure AI agents and LLM-powered applications.

Job Summary

We are seeking a motivated AI Platform Engineer with 2-3 years of relevant backend, platform, or applied AI engineering experience. The role will contribute to the organization's AI platform by implementing reusable components, orchestration workflows, model and tool integrations, and operational capabilities for production-grade AI systems. The successful candidate will work closely with Applied AI Engineers, software engineers, and platform teams to accelerate the delivery of reliable, observable, and scalable AI-powered solutions.

Key Responsibilities

• Contribute to the design, development, and maintenance of the shared AI platform used to build and deploy AI agents and LLM-powered services.
• Implement agent orchestration workflows using LangChain, LangGraph, or comparable frameworks.
• Develop reusable Python libraries, SDKs, templates, and APIs that simplify integration with models, tools, data sources, and internal systems.
• Build and maintain integrations with commercial and locally hosted LLMs, embedding models, vector stores, and internal AI services.
• Implement platform capabilities for prompt and configuration management, tool invocation, memory and state handling, agent execution, and evaluation.
• Integrate observability and evaluation tools, such as Langfuse or equivalent platforms, to monitor prompts, traces, latency, quality, token usage, and cost.
• Support retrieval-augmented generation (RAG) pipelines, including document ingestion, indexing, retrieval, and response grounding.
• Improve platform reliability, scalability, security, and performance through testing, automation, monitoring, and engineering best practices.
• Collaborate with Applied AI Engineers and product teams to translate application requirements into reusable platform capabilities.
• Produce clear technical documentation and contribute to code reviews, automated testing, CI/CD, and release activities.

Required Skills and Qualifications

• 2-3 years of relevant experience in backend engineering, platform engineering, software engineering, or applied AI development.
• Strong programming skills in Python, including experience developing APIs, services, or reusable packages.
• Practical exposure to building or integrating LLM-powered applications, AI agents, or generative AI services.
• Familiarity with LangChain, LangGraph, or similar agent and workflow orchestration frameworks.
• Working knowledge of prompt engineering, RAG patterns, embeddings, tool calling, and AI workflow orchestration.
• Understanding of REST APIs, microservices, asynchronous processing, and distributed systems concepts.
• Familiarity with software engineering practices, including Git, automated testing, CI/CD, and containerization.
• Understanding of application logging, monitoring, tracing, and observability principles.
• Bachelor's degree in Computer Science, Software Engineering, Artificial Intelligence, or a related discipline, or equivalent practical experience.

Preferred Qualifications

• Experience with vector databases, semantic search, or document ingestion pipelines.
• Exposure to AI observability and evaluation platforms such as Langfuse, LangSmith, or equivalent tools.
• Experience integrating with LLM providers such as Azure OpenAI/OpenAI, Anthropic, or locally hosted open-source models.
• Experience building reusable Python libraries, internal developer platforms, or developer tooling.
• Familiarity with Docker, Kubernetes, cloud platforms, and secure secrets and API management.
• Awareness of responsible AI, model governance, data privacy, and security principles.

Key Competencies

• Problem solving: Approaches ambiguous technical challenges methodically and proposes practical solutions.
• Learning agility: Keeps pace with a rapidly evolving AI ecosystem and applies new concepts thoughtfully.
• Collaboration: Works effectively across engineering, product, architecture, security, and operations teams.
• Quality and reliability: Takes ownership of maintainable code, testing, documentation, and production readiness.
• Communication: Explains technical decisions clearly and documents platform capabilities for other engineers.

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

Vertical:

Technology