Forward Deployment Engineer (m/f/d)

Halian; Abu Dhabi; On-site; AED 300,000 - 600,000; Full time

Job summary

Halian is building an in-house AI engineering capability to deliver enterprise AI solutions in Abu Dhabi. As a Forward Deployed AI Engineer, you will define the technical direction for an AI squad embedded within the business and own end-to-end delivery from discovery to production.

You will design, build, deploy, and operate agentic AI systems, work closely with Business Product Owners and AI Value Architects, and ensure scalable, secure, and compliant solutions across complex operations.

Qualifications

• 8+ years of production-grade software experience.
• 4+ years with Generative AI / LLMs / ML.
• 1+ year deploying agentic AI solutions.
• Experience setting technical direction at scale.

Responsibilities

• Own solution quality from inception to operation with testing and observability.
• Design multi-agent systems and tool orchestration patterns.
• Lead engagements with external AI platforms and partners.
• Mentor engineers and raise engineering standards.

Skills

Agentic AI

Python

Communication in English

MCP

Cloud deployment

Education

Master's degree in CS/SE/Data Science/AI/ML

Tools

FastAPI

Pydantic

CI/CD

LangGraph

Semantic Kernel

CrewAI

AutoGen

OpenAI Agents SDK

Microsoft Foundry

Amazon Bedrock AgentCore

Google Vertex AI / Gemini

Job description

We are building a world-class, in-house AI engineering capability to create and scale enterprise AI solutions for complex operational environments. We build, own, and continuously evolve our AI products rather than relying on off-the-shelf solutions.

As a Forward Deployed AI Engineer, you will define the technical direction for an AI squad embedded within the business. Working closely with stakeholders, you will understand business challenges and their underlying drivers, then design, build, deploy, and operate agentic AI systems that deliver measurable outcomes.

This is a highly hands-on, build-first role with end-to-end ownership of real business outcomes. You will partner with Business Product Owners and AI Value Architects while leveraging a shared AI platform, standards, and integration frameworks that enable teams to innovate rapidly and independently.

Key Accountabilities & Responsibilities

Understand Before You Build

Begin every initiative by understanding the business problem, objectives, and desired outcomes. Partner directly with stakeholders and lead solutions from discovery through production deployment.

AI Solution Development

• Design, build, deploy, and continuously improve enterprise-grade agentic AI applications using agentic development practices as the primary engineering approach.
• Develop AI agents capable of multi-step reasoning, tool and API orchestration, context management, exception handling, and human-in-the-loop workflows at enterprise scale.
• Design and implement Retrieval-Augmented Generation (RAG) solutions, including data ingestion, chunking strategies, embeddings, vector search, retrieval optimization, grounding, and source traceability.
• Build integrations using Model Context Protocol (MCP) and connect AI systems to enterprise platforms through REST APIs, OpenAPI specifications, webhooks, and event-driven architectures.
• Create reusable, self-service AI services and interfaces that can be leveraged across multiple business domains.
• Apply structured LLM engineering practices, including tool calling, schema validation, retries, fallbacks, and guardrails.

Quality, Reliability & Governance

• Own solution quality from inception through operation, including testing, evaluation, observability, logging, version control, and continuous feedback mechanisms.
• Optimize reliability, accuracy, performance, security, latency, and cost across deployed AI solutions.
• Ensure compliance with security, privacy, access controls, auditability, responsible AI principles, and governance requirements.

Technical Leadership

• Take ownership of business outcomes within a specific domain, ensuring successful delivery and measurable impact.
• Establish reusable patterns, frameworks, and engineering standards that strengthen internal AI capabilities.
• Collaborate effectively with Product Owners, AI Architects, and engineering teams, while challenging assumptions and identifying when AI is not the appropriate solution.
• Define technical direction, architecture standards, and strategic build-versus-buy decisions for AI initiatives.
• Design multi-agent systems, agent-to-agent communication patterns, and evaluation frameworks that ensure robustness and scalability.
• Lead engagements with external AI technology providers and partners while maintaining a strong focus on internal capability development.
• Mentor engineers, conduct technical reviews, and raise engineering standards across quality, security, and cost optimization.

Education & Experience

We are seeking a technical leader who combines deep engineering expertise in agentic AI with strong business acumen and a hands-on delivery mindset.

Core Requirements

• Demonstrated curiosity and a passion for understanding complex business and operational challenges.
• Strong business-first, human-centered approach, recognizing that AI augments people rather than replacing them.
• Excellent communication skills in English and experience working within diverse, international teams.
• 8+ years of experience building production-grade software, including:
  • 4+ years working with Generative AI, Large Language Models (LLMs), or applied Machine Learning.
  • At least 1 year of hands-on experience designing and deploying agentic AI solutions.
  • Proven success setting technical direction and delivering AI solutions at scale.
• Hands-on experience or strong working knowledge of Model Context Protocol (MCP) for connecting AI agents with systems, tools, APIs, and data sources.
• Strong Python programming skills and expertise in at least one of the following:
  • TypeScript / JavaScript
  • Java
  • C#
• Strong understanding of modern engineering practices, including asynchronous programming, FastAPI, Pydantic, CI/CD, testing strategies, source control, logging, and error handling.
• Experience with at least one agent framework or enterprise AI platform, such as:
  • LangGraph
  • Semantic Kernel
  • CrewAI
  • AutoGen
  • OpenAI Agents SDK
  • Microsoft Foundry
  • Amazon Bedrock AgentCore
  • Google Vertex AI / Gemini
• Experience with vector databases and search platforms such as:
  • Azure AI Search
  • pgvector
  • Pinecone
  • Weaviate
  • OpenSearch
• Experience integrating enterprise systems through APIs, managed identities, middleware, webhooks, messaging queues, and cloud-native architectures.
• Practical experience deploying solutions in cloud environments using containers, monitoring, and observability platforms.
• Strong judgment regarding trade-offs between quality, latency, reliability, security, governance, and cost.

Desirable Experience

• Experience in aviation, transportation, logistics, supply chain, cargo operations, customer service operations, or other complex operational environments.
• Background in classical machine learning, data science, or advanced analytics.
• Experience across full-stack software development, including front-end, API, and back-end engineering.

Preferred Experience

• Designing AI agents for enterprise-scale operational workflows.
• Voice AI, email automation, CRM integrations, workflow automation, or multilingual AI solutions.
• Building evaluation frameworks, golden datasets, simulation-based testing, regression testing, and AI quality measurement systems.
• Designing multi-agent architectures, agent registries, and tool orchestration standards.
• Leading delivery with external AI platforms, startups, or technology vendors while developing internal engineering teams and capabilities.

Education

• Master's degree in Computer Science, Software Engineering, Data Science, Artificial Intelligence, Machine Learning, or a related technical field; or equivalent practical experience.
• Relevant certifications in Cloud AI, Generative AI, Agentic AI, MLOps, or related disciplines are advantageous.