Solution Architect – LangGraph, Agentic AI

This is a fully remote position, open to applicants in Netherlands, +3 more countries.

📋 Description

• Oversee the architecture and design of enterprise AI agents and agent-based workflow solutions.

• Create LangGraph-based architectures for both single-agent and multi-agent applications.

• Convert business requirements, processes, SLAs, security needs, and technical constraints into solution architectures.

• Assess architectural alternatives and document significant technical decisions and trade-offs.

• Establish reusable architecture patterns tailored for agentic AI solutions.

• Design architectures that incorporate LLMs, LangGraph, RAG, enterprise data, APIs, business systems, workflow engines, human approval processes, observability, security, and governance.

• Define the separation between AI reasoning and deterministic business logic.

• Create designs for state management, persistence, recovery, and long-running agent workflows.

• Decide when to implement single-agent, multi-agent, or conventional application architectures.

• Develop scalable AI application architectures on platforms like AWS, Azure, or GCP.

• Specify compute, networking, storage, API, security, and platform requirements.

• Create architectures that are suitable for enterprise-scale production workloads.

• Assess cloud services and AI platform capabilities in terms of performance, security, scalability, and cost.

• Collaborate with platform engineering and DevOps teams to set deployment standards.

• Design the integration between AI agents and enterprise applications, APIs, databases, and SaaS platforms.

• Define secure methods for agent tool access and interactions with business systems.

• Create authentication, authorization, secrets management, and access-control strategies.

• Ensure that AI-driven actions are traceable, auditable, and properly governed.

• Establish security and governance principles for enterprise AI agents.

• Address issues such as prompt injection, data leakage, unauthorized tool usage, excessive agent permissions, inaccurate or unsafe actions, and sensitive data exposure.

• Define human-in-the-loop controls.

• Ensure compliance of solutions with organizational security, privacy, regulatory, and responsible AI standards.

• Create architecture for monitoring and observability of AI applications.

• Develop methods for evaluating agent accuracy, reliability, latency, cost, and task completion.

• Define logging, tracing, metrics, and alerting protocols.

• Establish operational processes for monitoring and continually enhancing production agents.

• Engage directly with senior business and technology stakeholders to define AI strategies and roadmaps.

• Lead architecture workshops and technical design discussions.

• Articulate complex AI concepts and architectural trade-offs to both technical and non-technical audiences.

• Provide technical guidance to AI engineers, developers, data teams, and platform engineers.

• Review solution designs to ensure they align with enterprise architecture standards.

• Mentor engineering teams and advocate for reusable AI architecture patterns.

⛳️ Requirements

• Extensive experience in solution architecture, software architecture, AI architecture, or a related field.

• Practical experience in designing and deploying LangGraph-based AI applications or agentic workflows.

• Strong grasp of LLM application architectures.

• Experience with enterprise AI/ML solutions in a production setting.

• In-depth understanding of RAG, tool calling, agent orchestration, and human-in-the-loop frameworks.

• Significant experience with at least one major cloud platform: AWS, Azure, or GCP.

• Comprehensive understanding of enterprise integration patterns and APIs.

• Familiarity with security, governance, observability, and operational needs for production systems.

• Strong technical knowledge of Python and contemporary software engineering practices.

• Desirable: Experience with LangChain / LangSmith.

• Desirable: Knowledge of multi-agent architectures.

• Desirable: Familiarity with enterprise RAG platforms.

• Desirable: Understanding of vector databases.

• Desirable: Experience with Kubernetes.

• Desirable: Knowledge of event-driven architectures.

• Desirable: Familiarity with microservices.

• Desirable: Experience with Infrastructure as Code.

• Desirable: Knowledge of CI/CD processes.

• Desirable: Understanding of MLOps / LLMOps.

• Desirable: Knowledge of AI security.

• Desirable: Familiarity with responsible AI practices.

• Desirable: Experience in large-scale enterprise transformation.

• Desirable: Experience working directly with senior client stakeholders.

🏝️ Benefits

• Opportunity to work at the forefront of AI technology.

• Access to continuous learning and development programs.

• Competitive salary and comprehensive benefits package.

• Collaborative and innovative work environment.