M

Madar

Mid-Senior AI Engineer - Generative AI & Agents

AI Application EngineeringConfirmed live in the last 24 hours
Full-timeCairo, Cairo Governorate, EgyptNo salary listedIn-person

About the Job

Requirements

  • A bachelor's degree in Computer Science, Software Engineering, Artificial Intelligence, Data Science, or a related technical field is required.
  • At least 4 years of software engineering experience, including approximately 1–2 or more years of hands-on experience building large language model or generative AI applications.
  • Strong programming skills in Python.
  • Strong understanding of software engineering principles, APIs, distributed systems, and production application development.
  • Practical experience building retrieval-augmented generation applications, including embeddings, vector databases, document processing, and retrieval techniques.
  • Experience designing and developing AI agents, tool-calling systems, and multi-step large language model workflows.
  • Hands-on experience with AI frameworks such as LangChain, LangGraph, Semantic Kernel, LlamaIndex, or equivalent.
  • Hands-on experience with major large language model platforms such as Claude, OpenAI, Azure OpenAI, Gemini, or equivalent.
  • Experience integrating AI capabilities into production applications and backend services.
  • Understanding of AI evaluation, prompt testing, retrieval-augmented generation evaluation, and AI application quality measurement.
  • Understanding of production AI concerns including reliability, latency, scalability, security, observability, and cost.
  • Ability to translate AI capabilities into practical business solutions.
  • Analytical and problem-solving capabilities.
  • Ability to collaborate across Product, Engineering, Data, Security, Platform, and Operations teams.

Responsibilities

  • Design and build AI-powered logistics capabilities, including shipment assistants, customer-support assistants, operational copilots, document intelligence, exception-handling workflows, and intelligent automation.
  • Contribute to predictive AI use cases such as ETA prediction, anomaly detection, operational risk identification, and shipment-related forecasting where appropriate.
  • Translate product, business, and operational requirements into practical and reliable AI solutions.
  • Work with Product and Engineering teams to move AI capabilities from proof of concept to production.
  • Design reusable AI components and services for use across Madar products and engineering teams.
  • Integrate AI services with existing Angular, Node.js, API, event-driven, and backend platforms.
  • Design, build, and maintain retrieval-augmented generation pipelines using embeddings, vector databases, structured data, unstructured documents, and logistics-domain information.
  • Implement document ingestion, chunking, indexing, retrieval, reranking, and context-management strategies.
  • Build AI applications using LLM platforms such as Claude, OpenAI, Azure OpenAI, Gemini, or equivalent enterprise AI platforms.
  • Use AI frameworks such as LangChain, LangGraph, Semantic Kernel, LlamaIndex, or equivalent frameworks where appropriate.
  • Design model-agnostic architectures to evaluate and adopt models based on capability, reliability, latency, security, and cost.
  • Improve retrieval relevance, grounding, response accuracy, and application reliability.
  • Design structured output and tool-calling patterns to connect LLMs reliably with business applications and backend services.
  • Design and develop AI agents for logistics workflows such as dispatch assistance, customer support, shipment exception handling, operations support, and internal productivity.
  • Build agentic workflows combining LLM reasoning, deterministic business rules, APIs, enterprise data, and external systems.
  • Implement state management, memory, tool usage, workflow orchestration, and human approval steps.
  • Define boundaries between AI-driven decisions and deterministic application logic.
  • Design human-in-the-loop workflows where AI-generated decisions or actions require review or approval.
  • Ensure AI agents operate within defined permissions and business boundaries.
  • Design evaluation frameworks and test datasets for measuring AI system performance.
  • Evaluate solutions for retrieval quality, groundedness, hallucination rate, task completion and success rate, response quality, accuracy, latency, reliability, token consumption, and cost.
  • Establish regression testing for prompts, retrieval pipelines, models, tools, and agent workflows.
  • Develop golden datasets and benchmark scenarios for critical AI use cases.
  • Apply human evaluation, automated evaluation, and LLM-as-a-judge approaches where appropriate.
  • Measure production AI performance and identify opportunities for improvement.
  • Apply secure AI engineering practices to protect customers, systems, and business data.
  • Implement controls against prompt injection, indirect prompt injection, sensitive information leakage, unauthorized data access, excessive agent permissions, unsafe tool execution, and cross-user or cross-tenant data exposure.
  • Design secure authorization models for retrieval-augmented generation applications and AI agents.
  • Ensure AI applications respect existing application-level access controls and data boundaries.
  • Apply secure secrets management and authentication when integrating AI services with internal and external systems.
  • Implement appropriate logging, tracing, and monitoring of AI interactions and actions to support auditability.
  • Work with Security and Platform teams to establish practical AI governance and security standards.
  • Drive adoption of Claude Code and other AI-assisted development tools across engineering teams.
  • Develop reusable AI skills, subagents, prompt templates, engineering instructions, and development workflows.
  • Help engineers use AI for coding, unit and integration testing, code reviews, debugging, documentation, refactoring, application migrations, and infrastructure and automation tasks.
  • Establish practical standards and engineering playbooks for AI-assisted software development.
  • Identify engineering workflows where AI can improve development velocity, quality, or operational efficiency.
  • Support responsible use of AI by engineering teams without compromising software quality, security, or maintainability.
  • Design AI services for scalability, availability, maintainability, and production readiness.
  • Build APIs and reusable services for AI functionality to be consumed by different applications.
  • Work with DevOps and Platform teams to establish CI/CD practices for AI applications.
  • Implement observability for AI services, including application tracing, model and prompt performance, request latency, token usage, model cost, error rates, and retrieval performance.
  • Monitor production AI applications and identify operational or quality issues.
  • Optimize solutions for quality, latency, throughput, infrastructure cost, and model/API cost.
  • Support versioning and controlled rollout of models, prompts, embeddings, retrieval strategies, and agent workflows.
  • Build or support predictive models for ETA prediction, anomaly detection, classification, forecasting, or operational intelligence where traditional machine learning is appropriate.
  • Perform feature engineering and model evaluation using historical operational data.
  • Select statistical, machine-learning, or deep-learning techniques based on the problem rather than defaulting to LLM-based solutions.
  • Work with Data and Platform teams to operationalize machine-learning models where required.

Desired Qualifications

  • Experience with Node.js or TypeScript and integration with modern web application architectures.
  • Experience with Angular or similar frontend frameworks.
  • Experience with logistics, transportation, supply chain, e-commerce, or B2B technology platforms.
  • Experience implementing AI agents in production environments.
  • Experience with Claude Code or similar AI-assisted software-development platforms.
  • Experience with MLOps, AI observability, model lifecycle management, or AI production infrastructure.
  • Experience with traditional machine-learning frameworks such as scikit-learn, XGBoost, LightGBM, PyTorch, or equivalent.
  • Experience with OCR, document intelligence, document classification, or intelligent document processing.
  • Experience with fine-tuning, model customization, or parameter-efficient fine-tuning techniques.
  • Experience with Azure AI services, Azure OpenAI, or other cloud-based AI platforms.
  • Experience implementing enterprise AI security, AI governance, or responsible-AI practices.
  • Experience designing AI solutions for multi-tenant, enterprise, or B2B SaaS platforms.

About the Company

Madar

Company size
Not listed
Company stage
Not listed
Total funding
Not listed
Headquarters
Rennes, France
Founded
2019

Recently Posted Jobs

Explore more opportunities at Madar

See more jobs