Integrant

Enterprise software engineering with AI agents

Senior Lead Agentic Developer

AI Application EngineeringConfirmed live in the last 24 hours

Full-timeCairo, Cairo Governorate, EgyptNo salary listed

About the Job

Requirements

At least 8 years of professional software engineering experience, including at least 1–2 years shipping LLM-based systems to production users.
Strong proficiency in Python or TypeScript and working proficiency in the other, plus comfort with asynchronous programming, API design, and typed data models such as Pydantic or Zod.
Experience building at least one production agent that runs a real multi-step workflow with tool calls, including explaining its failure modes and fixes.
Hands-on experience with at least one orchestration framework such as LangGraph, OpenAI Agents SDK, Bedrock Agents, AutoGen, CrewAI, or a similar framework, and ability to explain its abstractions and when to use raw API calls.
Practical retrieval-augmented generation experience, including vector and hybrid search, chunking strategy, re-ranking, and retrieval evaluation.
Experience writing evaluations for LLM systems and treating prompt changes as code changes with regression coverage.
Working knowledge of observability tooling, including OpenTelemetry-style tracing or LLM tracing platforms such as LangSmith, Langfuse, Arize, or equivalent.
Understanding of LLM security threats such as prompt injection, data leakage, and excessive agency, and standard mitigations.
Experience integrating enterprise systems through REST or GraphQL APIs, webhooks, or message queues, including authentication flows such as OAuth 2.0 or service accounts.
Experience with workflow engines such as Temporal, Durable Functions, or Step Functions for long-running agent processes.
Experience implementing a Model Context Protocol server or client.

Responsibilities

Design single-agent and multi-agent systems, selecting the simplest suitable planner/executor, supervisor/worker, hierarchical, or event-driven pattern.
Model agent workflows as explicit state machines or graphs with defined states, transitions, retries, timeouts, and human-in-the-loop checkpoints.
Define tool contracts, including schemas, idempotency, and error semantics, and implement tool-calling with validation and graceful degradation.
Implement short-term context management, long-term memory stores, and session persistence with clear retention rules.
Build and tune retrieval pipelines using chunking, embeddings, hybrid search, re-ranking, metadata filtering, and query rewriting.
Support permissions-aware retrieval, multi-tenant isolation, and freshness and synchronization from source systems.
Measure retrieval quality, including recall, precision, and groundedness, and improve it at the pipeline level.
Build evaluation suites before shipping, including golden datasets, task-level success metrics, calibrated LLM-as-judge evaluations, and regression tests for each change.
Write unit and integration tests for tools, state transitions, and guardrails.
Run offline and online evaluations and use A/B or shadow deployments to validate changes against production traffic.
Instrument agents end-to-end with per-run traces, token and cost accounting, per-step latency, tool-call outcomes, and failure classification.
Define agent service-level objectives for success rate, p95 latency, and cost per task, and build dashboards and alerts.
Operate agents in production, participate in on-call, analyze incidents, and identify root causes of model and non-model failures.
Implement defenses against prompt injection, data exfiltration, and tool misuse, and enforce least privilege for each tool and integration.
Apply input/output guardrails, personally identifiable information handling, content policies, and audit logging that satisfies enterprise compliance.
Design human-approval gates for high-impact actions and make agent decisions explainable to auditors and business owners.
Integrate agents with enterprise resource planning, customer relationship management, IT service management, document management, and identity systems via APIs, event streams, and Model Context Protocol-style tool servers.
Handle authentication and authorization on behalf of users, including OAuth, service principals, and delegated access.
Build agents that handle inconsistent records, partial failures, rate limits, and legacy interfaces.
Translate business processes into agent specifications with clear success criteria and return-on-investment measures.
Produce architecture decision records, runbooks, and handover documentation.
Mentor engineers transitioning into agentic development and review designs and code for agent-specific pitfalls.

Desired Qualifications

Cloud deployment experience with Azure, AWS, or Google Cloud Platform, containers, and continuous integration and continuous delivery.
Fine-tuning or distillation experience, or experience optimizing structured output and function calling at scale.
Knowledge-graph or semantic-layer experience for grounding agents.
Exposure to regulated environments such as SOC 2, HIPAA, or GDPR, and audit requirements.
Prior consulting or client-facing delivery experience.

Senior Lead Agentic Developer

Integrant · Cairo, Egypt (Hybrid) · Full-time · Posted 2026-10-29

Workplace: hybrid

Department: Software Development

Description

About Integrant

_For 34 years, Integrant has designed and delivered advanced, business solutions for U.S. enterprises in biotech, medical devices, manufacturing, finance, and related highly regulated industries. Our teams are experts in traditional web and mobile applications, AI/HPC infrastructure support, data engineering, predictive AI, machine learning, and Agentic solutions. We build long-term partnerships—two-thirds of our customers choosing to partner with us 5+ years—by solving mission-critical problems with rigor, empathy, and measurable outcomes.

_Role overview

Title: Agentic Developer (Enterprise Agentic Systems)

Mission: Build production-grade AI agents that run real business processes inside enterprise environments — reliably, securely, observably, and with measurable ROI.

This is not a prompt-engineering or demo-building role. The person we hire owns the full lifecycle of an agent: design, implementation, evaluation, deployment, monitoring, and iteration. They treat an agent as a distributed software system with a probabilistic component, not as a chatbot with tools attached.

Stack-agnostic by design. We use Python and TypeScript, and frameworks such as LangGraph, the OpenAI Agents SDK, Bedrock Agents, and Copilot Studio appear in our work as examples, not requirements. We hire for the underlying engineering judgment: someone who can pick up any orchestration framework in a week because they understand what every framework is abstracting.

Key responsibilities:

1. Agent design & orchestration

Design single-agent and multi-agent systems: planner/executor, supervisor/worker, hierarchical, and event-driven patterns, choosing the simplest pattern that meets the requirement.
Model agent workflows as explicit state machines or graphs with defined states, transitions, retries, timeouts, and human-in-the-loop checkpoints.
Define tool contracts (schemas, idempotency, error semantics) and implement tool-calling with validation and graceful degradation.
Implement memory strategies: short-term context management, long-term memory stores, and session persistence with clear retention rules.

2. Retrieval & knowledge (RAG at scale)

Build and tune retrieval pipelines: chunking, embedding, hybrid search, re-ranking, metadata filtering, and query rewriting.
Handle enterprise document realities: permissions-aware retrieval, multi-tenant isolation, freshness and sync from source systems.
Measure retrieval quality (recall, precision, groundedness) and fix it at the pipeline level, not the prompt level.

3. Evaluation, testing & quality

Build eval suites before shipping: golden datasets, task-level success metrics, LLM-as-judge with calibration, regression tests on every change.
Write unit and integration tests for tools, state transitions, and guardrails; test the non-LLM 80% like any other software.
Run offline and online evals; use A/B or shadow deployments to validate changes against production traffic.

4. Observability & operations

Instrument agents end-to-end: traces per run, token/cost accounting, latency per step, tool-call outcomes, and failure classification.
Define SLOs for agents (success rate, p95 latency, cost per task) and build dashboards and alerts against them.
Operate agents in production: on-call participation, incident analysis, root-cause on model and non-model failures.

5. Security, safety & governance

Implement defenses against prompt injection, data exfiltration, and tool misuse; enforce least-privilege for every tool and integration.
Apply input/output guardrails, PII handling, content policies, and audit logging that satisfies enterprise compliance.
Design human-approval gates for high-impact actions and make agent decisions explainable to auditors and business owners.

6. Enterprise integration

Integrate agents with ERP, CRM, ITSM, document management, and identity systems via APIs, event streams, and MCP-style tool servers.
Handle authentication and authorization on behalf of users (OAuth, service principals, delegated access) correctly.
Build agents that survive real data: inconsistent records, partial failures, rate limits, and legacy interfaces.

7. Delivery & collaboration

Translate business processes into agent specifications with clear success criteria and ROI measures.
Produce architecture decision records, runbooks, and handover documentation.
Mentor engineers transitioning into agentic development; review designs and code for agent-specific pitfalls.

Requirements

Must-have

8+ years of professional software engineering, with at least 1–2 years shipping LLM-based systems to production users.
Strong in Python or TypeScript, working proficiency in the other; comfortable with async programming, API design, and typed data models (e.g., Pydantic/Zod).
Has built at least one agent that runs a real multi-step workflow with tool calls in production, and can describe its failure modes and how they were fixed.
Hands-on with at least one orchestration framework (LangGraph, OpenAI Agents SDK, Bedrock Agents, AutoGen, CrewAI, or similar) and able to explain what it abstracts and when to drop to raw API calls.
Practical RAG experience: vector and hybrid search, chunking strategy, re-ranking, and retrieval evaluation.
Experience writing evals for LLM systems and treating prompt changes as code changes with regression coverage.
Working knowledge of observability tooling (OpenTelemetry-style tracing, LLM tracing platforms such as LangSmith, Langfuse, Arize, or equivalent).
Understanding of LLM security threats (prompt injection, data leakage, excessive agency) and standard mitigations.
Experience integrating with enterprise systems through REST/GraphQL APIs, webhooks, or message queues, including auth flows (OAuth 2.0, service accounts).
Experience with workflow engines (Temporal, or Durable Functions, or Step Functions) for long-running agent processes.
Model Context Protocol (MCP) server or client implementation.

Nice-to-have

Cloud deployment experience (Azure, AWS, or GCP) with containers and CI/CD
Fine-tuning or distillation experience, or structured-output and function-calling optimization at scale.
Knowledge-graph or semantic-layer experience for grounding agents.
Exposure to regulated environments (SOC 2, HIPAA, GDPR) and audit requirements.
Prior consulting or client-facing delivery experience.

Benefits

Competitive compensation package
PTO, full medical and dental coverage, etc.
Opportunity to travel and work onsite with U.S. customers
In-house Technical and English training programs
Dedicated learning time (check out our 4Plus1 Program)
Interest free loans
Flexible work schedules
Perks: events, sponsored lunch, game area, rooftop hangout + more!

Apply

Apply at Integrant

About the Company

Integrant

Enterprise software engineering with AI agents

Integrant builds enterprise software for regulated industries like medical devices, life sciences, pharma, financial services, manufacturing, and the public sector. Their offerings include full platform development, modernization of legacy systems, or embedding AI agents into client workflows. It uses the Agentic Software Development Life Cycle (ADLC), where AI agents assist across requirements, architecture, build, test, and deployment, while engineers with deep domain knowledge govern every step to ensure quality. Unlike many firms, Integrant combines top-tier engineering talent (the top 1% in a demanding market), a long-track record in regulated environments, and responsible AI acceleration with engineer accountability. Their goal is to be the trusted technology partner clients rely on for mission-critical software that lasts. Headquartered in San Diego with engineering centers in Cairo and Amman.

Company size: 201-500
Company stage: Not listed
Total funding: Not listed
Headquarters: San Diego, CA
Founded: 1992

Recently Posted Jobs

Explore more opportunities at Integrant

See more jobs