Artificial Intelligence Engineer

Albatha Group; Dubai; On-site; AED 250,000 - 450,000; Full time

Job summary

Albatha Group is seeking an AI Engineer to embed with customer teams and turn AI demos into production systems. You will own the full arc from problem understanding to deployment in real environments, balancing technical rigor with business value.

The role requires shipping LLM-based solutions, evaluating AI systems, and working across data pipelines, cloud, and on-prem setups. Travel to client sites is expected.

Qualifications

• 5+ years of AI experience.
• Strong Python and TypeScript experience.
• Hands-on shipping LLM apps to production (prompt design, RAG, agents, tool use, structured outputs, fine-tuning).
• Experience with evaluating AI systems, test sets, LLM-as-judge methods, and tracking regressions.
• Experience with vector search, embeddings, data pipelines, SQL and API integration.
• Cloud infra (AWS/GCP/Azure), containers, and CI/CD.

Responsibilities

• Embed with customer teams to understand workflows, data, and constraints and identify AI value.
• Scope and prioritize use cases with stakeholders and turn problems into delivery plans.
• Design and build production AI solutions: LLM-based agents, RAG, tooling, document processing, automation.
• Integrate with customer systems (cloud, data warehouses, CRM, APIs).
• Build evaluation harnesses and monitoring for quality, latency, cost, safety.
• Deploy and operate solutions in customer environments with security/compliance.
• Iterate post-launch with end users, tuning prompts, retrieval, models, UX.
• Turn recurring needs into reusable components and provide feedback to product/research.
• Present results and roadmaps to executives and engineers.

Skills

Python

TypeScript

LLM production

AI evaluation

Vector search

Cloud & CI/CD

Travel readiness

Tools

LLM-based agents

RAG

Tool/function calling

Document processing

Workflow automation

Data warehouses / APIs

Job description

About the role

As an AI Engineer at Albatha Group, you embed with our customers to turn AI from a promising demo into a production system that moves their business. You will own the full arc: understand the customer's problem, design and build LLM-powered solutions, deploy them into messy real-world environments, and feed what you learn back into our product.

This role suits engineers who like being close to the problem, can write production-grade code, and are equally comfortable in a whiteboard session with a VP and a debugging session with a data team.

What you'll do

• Embed with customer teams to understand their workflows, data, and constraints, and identify where AI can deliver measurable value.
• Scope and prioritize use cases with technical and business stakeholders, turning ambiguous problems into clear delivery plans.
• Design and build production AI solutions: LLM-based agents, retrieval-augmented generation (RAG), tool/function calling, document processing, and workflow automation.
• Integrate with customer systems such as data warehouses, CRMs, ticketing tools, internal APIs, and legacy software.
• Build evaluation harnesses and monitoring so quality, latency, cost, and safety are measured, not guessed.
• Deploy and operate solutions in customer environments, including cloud, VPC, and on-prem setups with security and compliance requirements.
• Iterate with end users after launch, tuning prompts, retrieval, models, and UX based on real usage.
• Turn repeated customer needs into reusable components, and bring product and research teams concrete feedback from the field.
• Present results, trade-offs, and roadmaps to executives and engineers alike.

What you'll bring

• 5+ years of AI experience, with strong Python and working fluency in TypeScript or a similar language.
• Hands-on experience shipping LLM applications to production: prompt design, RAG, agents, tool use, structured outputs, and fine-tuning where it fits.
• Practical knowledge of evaluating AI systems, including building test sets, using LLM-as-judge methods, and tracking regressions.
• Experience with vector search, embeddings, and data pipelines, plus solid SQL and API integration skills.
• Comfort with cloud infrastructure (AWS, GCP, or Azure), containers, and CI/CD.
• Clear communication with both technical and non-technical audiences, including the ability to run workshops and explain trade-offs plainly.
• A bias for ownership: you take a problem from vague request to deployed, working solution.
• Willingness to travel to customer sites as needed (see logistics below).

Nice to have

• Prior experience in a forward deployed, solutions engineering, consulting, or startup founding role.
• Experience with agent frameworks, Model Context Protocol (MCP), or multi-agent orchestration.
• Background in a regulated industry such as finance, healthcare, or government, including security reviews and data governance.
• Familiarity with model serving, inference optimization, or open-weight model deployment.
• Experience with front-end work to build quick internal tools and prototypes for customers.
• Contributions to open-source AI tooling or published technical writing.