Senior Lead Agentic Developer

About the role

Integrant, which has delivered advanced business solutions for U.S. enterprises in biotech, medical devices, manufacturing and finance for 34 years, is hiring a Senior Lead Agentic Developer in Cairo. The role builds production-grade AI agents that run real business processes inside enterprise environments, reliably, securely and with measurable ROI. It is not a prompt-engineering or demo-building role: the person hired owns the full lifecycle of an agent, from design and implementation to evaluation, deployment, monitoring and iteration.

Key responsibilities

• Design and orchestrate single-agent and multi-agent systems, including planner/executor, supervisor/worker, hierarchical and event-driven patterns, with memory strategies and tool contracts.
• Build and tune retrieval pipelines (chunking, embeddings, hybrid search, re-ranking, metadata filtering) and measure retrieval quality.
• Build eval suites (golden datasets, LLM-as-judge, regression tests) and write unit and integration tests for tools and guardrails.
• Instrument agents end-to-end (traces, token/cost accounting, latency, failure classification), define SLOs and operate agents in production with on-call and incident response.
• Implement security and governance: prompt injection and data exfiltration defenses, least privilege, input/output guardrails, PII handling, audit logging and human-approval gates.
• Integrate agents with ERP, CRM, ITSM and document management systems via APIs, event streams and tool servers, handling authentication and authorization.
• Translate business processes into agent specifications, produce architecture decision records and runbooks, and mentor engineers.

Required profile

• 8+ years of professional software engineering, with at least 1-2 years shipping LLM-based systems to production users.
• At least one agent running a real multi-step workflow with tool calls in production, with described failure modes and fixes.
• Hands-on experience with at least one orchestration framework (LangGraph, OpenAI Agents SDK, Bedrock Agents, AutoGen, CrewAI or similar).
• Practical RAG experience and experience writing evals for LLM systems.
• Working knowledge of observability tooling (OpenTelemetry-style tracing, LangSmith, Langfuse, Arize or equivalent).
• Understanding of LLM security threats and mitigations.
• Experience integrating with enterprise systems via REST/GraphQL, webhooks or message queues, including OAuth 2.0 and service accounts.
• Experience with workflow engines (Temporal, Durable Functions or Step Functions) and Model Context Protocol (MCP) server or client implementation.

Required skills

• Strong Python or TypeScript, with working proficiency in the other; async programming, API design and typed data models (Pydantic/Zod)
• RAG: vector and hybrid search, chunking, re-ranking, retrieval evaluation
• Workflow engines (Temporal, Durable Functions, Step Functions)
• Nice to have: cloud deployment (Azure, AWS, GCP) with containers and CI/CD, fine-tuning or distillation, knowledge-graph or semantic-layer experience, SOC 2/HIPAA/GDPR exposure, consulting experience

What we offer

• Competitive compensation package with PTO, full medical and dental coverage
• Opportunity to travel and work onsite with U.S. customers
• In-house technical and English training programs and dedicated learning time
• Interest-free loans, flexible work schedules and perks such as events, sponsored lunch and a game area