Senior Agentic AI Engineer

About Bright Brains

Bright Brains is expanding its technology portfolio with the launch of a dedicated Artificial Intelligence division, focused on building production-grade AI solutions for enterprises across the Middle East and international markets.

The new division will focus on agentic AI, enterprise AI automation, AI copilots, multi-agent systems, intelligent workflows, retrieval-augmented generation, enterprise integrations, and governed AI platforms.

Our objective is not to build demonstrations or isolated AI prototypes. We are building secure, reliable, deployable AI solutions that solve real business problems and integrate directly into enterprise environments.

As part of this expansion, we are building a core AI engineering team that will help establish the technical foundations, delivery standards, architecture, and reusable capabilities of the new division.

Role Mission

We are looking for a senior AI engineer and technical leader who can turn ambiguous business challenges into reliable, secure, production-ready AI products.

You will design, build, deploy, and continuously improve agentic AI systems that execute real enterprise workflows.

You will also lead and mentor junior AI and software engineers, establish strong engineering practices, and ensure consistently high delivery quality across AI projects.

This is a hands-on technical leadership position. You will own projects from discovery and architecture through implementation, evaluation, deployment, and production monitoring.

What You'll Do

• Lead, mentor, and technically support a team of junior AI and software engineers.
• Translate complex business requirements into clear and achievable engineering tasks.
• Review code, architecture, testing strategies, and technical documentation.
• Establish engineering standards, reusable architecture patterns, development frameworks, and delivery practices for Bright Brains AI division.
• Help junior engineers strengthen their technical judgment, problem-solving capabilities, and engineering discipline.
• Design and build AI agents capable of reasoning, using tools, retrieving evidence, maintaining state, and completing multi-step business workflows.
• Architect both single-agent and multi-agent systems with clearly defined responsibilities, boundaries, and control mechanisms.
• Integrate AI agents with enterprise APIs, databases, documents, SaaS platforms, business applications, and internal systems.
• Build production-grade RAG pipelines incorporating citations, permissions, access controls, and measurable retrieval quality.
• Implement human-approval workflows, governance controls, audit trails, rollback mechanisms, and policy enforcement.
• Develop evaluation frameworks covering correctness, hallucination, tool usage, safety, latency, reliability, and cost.
• Diagnose AI system failures using traces, logs, automated tests, evaluation datasets, and production feedback.
• Deploy AI services using containers across cloud, hybrid, and on-premise environments.
• Work directly with product, security, domain experts, customers, and delivery teams.
• Clearly communicate delivery status, technical risks, dependencies, and architectural decisions.
• Ensure systems remain maintainable, secure, testable, scalable, and production-ready.

Required Qualifications

• 4+ years of professional experience in software engineering, machine-learning engineering, applied AI, or a related technical discipline.
• Experience leading, mentoring, or technically supervising junior engineers.
• Strong ability to delegate engineering work while retaining accountability for final technical quality.
• Strong production-level Python experience.
• Demonstrated experience delivering at least one substantial LLM, generative AI, or agentic AI solution beyond a tutorial, proof of concept, or prompt-based prototype.
• Strong understanding of:
• Tool and function calling
• Agent state management and orchestration
• Structured outputs
• Retrieval, ranking, and reranking
• Prompt and context engineering
• Evaluation and failure analysis
• AI reliability, governance, and security
• Experience designing and consuming REST APIs.
• Strong knowledge of databases, data modeling, Git, testing, debugging, and software engineering fundamentals.
• Experience with Docker and production deployment.
• Ability to convert unclear or evolving business requirements into measurable technical outcomes.
• Strong code-review, planning, architecture, and technical decision-making skills.
• Clear written and verbal communication skills in English.

Strong Advantage

Experience with several of the following would be highly valuable, although experience with all of them is not required:

• LangGraph, Semantic Kernel, AutoGen, CrewAI, or custom agent-orchestration frameworks.
• Model Context Protocol (MCP) and secure AI tool integrations.
• Vector databases, semantic search, and hybrid retrieval.
• FastAPI, Pydantic, PostgreSQL, Redis, queues, and background workers.
• Azure, AWS, Google Cloud, Kubernetes, or enterprise on-premise deployments.
• LLM observability, tracing, monitoring, and evaluation platforms.
• Fine-tuning, inference optimization, or deployment of open-weight models.
• Enterprise identity management, RBAC, audit logging, governance, and data-residency controls.
• Arabic-language AI solutions and multilingual AI applications.
• Experience delivering solutions for banking, government, legal, IT operations, cybersecurity, or other regulated enterprise environments.

Why Join Bright Brains

This role provides the opportunity to join Bright Brains at an important stage of its growth and help shape a new AI division from the ground up.

You will have the opportunity to influence:

• The technical architecture of our AI platforms.
• The engineering standards and development methodology of the AI team.
• The selection of AI models, frameworks, and technologies.
• The design of reusable AI agents and enterprise automation capabilities.
• The development and mentoring of the broader AI engineering team.
• The delivery of real enterprise AI solutions across multiple industries and markets.

We are looking for someone who wants to do more than build AI prototypes. We want an engineer and technical leader who can help Bright Brains build enterprise-grade AI capabilities that move reliably from idea to production.