Team: Build, Frontier Firm Live (FFL)

We are scaling enterprise-grade agentic AI across the Middle East and Africa. Build is the engine room behind that work: the team that designs, ships, and continuously improves the AI agents and platform features inside our Frontier Firm Live offering. We are looking for a senior builder, someone who has shipped production AI systems before and can take that experience into a fast-moving, low-hierarchy team where engineers work directly alongside architects, designers, and AI strategists to turn high-value use cases into deployed solutions.

This is a senior role. Beyond building, you will set the standard other AI Engineers build to, review their architecture before delivery starts, and help shape the reference patterns that ship into our UseCaseLibrary across every customer engagement in the region.

➤ Production AI agents using Microsoft Foundry Agent Service: multi-agent workflows, hosted agents, memory, observability, identity integration, secure endpoints, and deployment

➤ Knowledge-grounded experiences using Azure AI Search and retrieval-augmented generation, including vectors, keyword-searchable, hybrid, semantic-ranking and enterprise-permissioned retrieval (When do we need vectorization and when we don’t, when to create handovers between agents, when to rely on the model’s context window, when to finetune and when to use RAG)

➤ Deterministic, source-grounded extraction: pipelines that pull figures and facts straight from documents without hallucinating, attaching citations, provenance and uncertainty flags to every claim so outputs are auditable

➤ Tool-using agents that execute secure actions through Model Context Protocol (MCP), Azure Logic Apps, Azure Functions, and custom APIs

➤ Model-optimised applications using Foundry Models and the model router, balancing quality, latency, and cost

➤ Enterprise-safe systems with prompt shielding, groundedness checks, and content-safety enforcement

➤ Reusable reference agents, connectors, and evaluation templates that ship into our UseCaseLibrary and accelerate delivery across the region

➤ Translate business opportunities into robust, production-ready agent architectures

➤ Build pro-code AI agents using Python (FastAPI, Streamlit, Scraping, Serialization, etc..), .NET React.js with the Microsoft Agent Framework (Knowing Langgraph/Langchain/Semantic Kernel is an edge)

➤ Lead the design of multi-agent orchestration and agentic design patterns, including planning, routing, and human-in-the-loop patterns, on the team's most complex builds (understanding distributed systems is a plus)

➤ Review architecture and delivery plans from other AI Engineers before build starts, and act as a technical escalation point during delivery

➤ Design and maintain the delivery lifecycle for agents already in production — evaluation, telemetry, logging, safety, and CI/CD pipelines — using GitHub Actions and pipeline YAML, with infrastructure-as-code (Bicep or Terraform) a plus

➤ Familiarity with networking concepts — VNets, subnets, private endpoints (and private DNS), NSGs, and firewall / allowlisting — for deploying AI services securely inside an enterprise tenant.

➤ Familiarity with data engineering and pre-processing — parsing, cleaning, normalization, deduplication and schema creation and engineering/validation (for quantitative and qualitative metrics) — so the data feeding agents and retrieval is clean, typed and reliable.

➤ Understanding model capabilities, benchmarks and limitations — and how to work around them: training-data knowledge cut-off, prompt-injection, context and harness engineering, retrieval grounding, and fine-tuning.

➤ Set and maintain the reference patterns and reusable components other engineers build from

➤ Mentor AI Engineers, including colleagues moving into the role through our internal upskilling path

➤ Support presales and customer proposals with technical input on feasibility and solution design

➤ Significant hands-on experience building production AI agents or AI-infused applications, not just prototypes

➤ Strong software engineering skills in Python or .NET, including modern cloud-integration patterns

➤ Hands-on experience with Microsoft Foundry: projects, SDKs, models, the model router, hosted agents, and Foundry tools

➤ Demonstrable experience building complete agentic workflows in Foundry Agent Service, including tool invocation and deployment

➤ Deep understanding of Azure AI Search and retrieval-augmented generation patterns, including vector, hybrid, and multimodal retrieval

➤ Practical experience implementing AI safety features: prompt shields, groundedness checks, and sensitive-content filters

➤ Experience with Azure Logic Apps, Azure Functions, Model Context Protocol (MCP) tools, and secure enterprise integrations

➤ Strong understanding of Microsoft Entra ID and enterprise governance best practice

➤ Experience reviewing other engineers' technical work and giving direct, constructive feedback

➤ Daily proficiency with GitHub Copilot, including effective use of GitHub Copilot Chat in real development work

➤ Comfort with CI/CD pipelines, telemetry, evaluation metrics, and iterative delivery

➤ Backend and streaming services: designing and operating asynchronous APIs (FastAPI/ASGI, or ASP.NET) with streaming responses, middleware, and clean configuration and secrets handling

➤ Distributed-systems fundamentals: concurrency, parallelism and threading, sticky sessions, async I/O, background tasks and queues, idempotency, and correct state across multiple replicas — the basis for reliable multi-agent orchestration at scale

➤ Deterministic, source-grounded extraction: reading numbers and facts from documents without hallucination, with citations, provenance and uncertainty flags — and sound judgement on chunking, embeddings and retrieval behind it

➤ Observability and evaluation depth: distributed tracing, telemetry and structured logging, plus offline and online evaluation pipelines that quantify quality and catch regressions before and after release

➤ Containerisation and delivery: Docker and CI/CD (for example GitHub Actions), deployment to managed compute, and a working knowledge of databases — relational (PostegresDB, CosmosDB), NoSQL and vector — for agent state, history and grounding

➤ Experience extending Microsoft 365 Copilot with custom agents, plugins, or connectors

➤ Familiarity with Prompt Flow for rapid prototyping and evaluation of LLM applications

➤ Exposure to Microsoft Fabric, Dynamics 365, ServiceNow, or SAP integration patterns

➤ Kubernetes experience for container orchestration and scaling of custom agent runtimes

➤ Prior experience mentoring junior or upskilling engineers

➤ Experience working with enterprise customers across the Middle East and Africa

Certifications That Help

Not required, but a strong signal of current Microsoft AI engineering skills:

➤ AI-103: Developing AI Apps and Agents on Azure (Microsoft's current Azure AI engineering path, built around Microsoft Foundry, generative AI, and agents)

➤ GH-300: GitHub Copilot Certification

How We Work

Sulava MEA is a Frontier Firm: fast, clear, and deeply collaborative. Our culture is built on trust, expertise, and action. We value people who think boldly, deliver impact, and raise the bar for modern AI engineering.

You will have access to top Microsoft expertise, MVP-level mentorship, ongoing learning opportunities, and projects that matter. Benefits include health insurance, flexible working arrangements, a professional development budget, and relocation support where applicable.

Please include the following two items with your application. They help us understand the impact you have delivered and how you communicate and work.

Cover Letter: Project Overview

Please include a brief cover letter outlining your highest-impact projects delivered over the past 12 months. Kindly highlight the key technical details, your role in the delivery, and the measurable outcomes achieved. This helps us gain a clearer understanding of your experience and working style.

Optional Video Introduction

Please include a link to a short video introducing yourself and your capabilities. The video does not need to be professionally produced, a simple recording is perfectly fine. This helps us get to know you better and understand your communication and presentation style.

➤ First interview: with our Lead Architects, to assess your technical background and get to know you

➤ Additional technical interview: may be required depending on what you showcase in your first interview

➤ Final interview: with the Head of AI Build at Sulava