AI Orchestrator & Workflow Architect

We are seeking an execution-focused AI Orchestrator & Workflow Architect to design, build, and deploy end-to-end AI-enabled business systems. This role is intended for a highly adaptable technology professional who understands how to combine generative AI platforms, autonomous agents, software applications, data sources, APIs, and workflow automation tools into practical solutions that improve how an organization operates.

The successful candidate will not be limited to a single model, framework, or development methodology. They will understand the strengths and limitations of leading commercial and open-source AI ecosystems and will select the right combination of tools for each use case. These may include Claude, ChatGPT, Gemini, GitHub Copilot, Cursor, Codex, v0, Replit, LangChain, CrewAI, Flowise, Make, n8n, and emerging platforms.

This is not a traditional machine learning research role, nor is it solely a low-code automation position. It is a hands-on solutions role for someone who can take an ambiguous operational or commercial problem, map it into a structured system, rapidly build a functional solution, and guide that solution into production and adoption.

The AI Orchestrator & Workflow Architect will bridge business strategy and technical execution. They will act as a force multiplier across the organization by accelerating experimentation, reducing manual work, connecting fragmented systems, and creating intelligent workflows that can scale responsibly.

Core Responsibilities

AI Platform Orchestration and Multi-Tool Strategy

• Serve as a central architect for the organization's generative AI and automation stack, selecting the most appropriate models, platforms, development environments, and orchestration tools for each requirement.

• Evaluate and integrate commercial and open-source AI ecosystems, including solutions from OpenAI, Anthropic, Google, Microsoft, and other emerging providers.

• Design model-agnostic architectures that allow systems to use different models based on accuracy, reasoning capability, speed, privacy, availability, and cost.

• Combine conversational AI, coding assistants, multimodal models, search, structured data tools, automation platforms, and traditional software components into cohesive solutions.

• Use AI-assisted development environments such as GitHub Copilot, Cursor, Codex, Claude Code, v0, and Replit to accelerate prototyping, application development, testing, and documentation.

• Maintain a working understanding of new model releases, agent capabilities, orchestration patterns, and AI development tools, and translate relevant advances into measurable operational improvements.

• Establish reusable templates, connectors, prompt libraries, workflow components, and implementation standards that enable teams to build AI solutions more quickly and consistently.

Agentic Workflow and Autonomous System Design

• Design and build autonomous and semi-autonomous agent systems that can reason through tasks, retrieve information, invoke tools, make bounded decisions, and complete multi-step workflows.

• Translate complex business processes into structured agent workflows with clearly defined objectives, roles, inputs, outputs, decision points, escalation paths, and completion criteria.

• Develop multi-agent systems in which specialized agents communicate, delegate work, validate outputs, and coordinate toward a shared business objective.

• Implement memory, context management, state persistence, task queues, retries, and exception-handling mechanisms appropriate to the workflow.

• Create robust human-in-the-loop checkpoints for approvals, sensitive decisions, ambiguous cases, and high-impact actions.

• Build validation loops, policy checks, confidence thresholds, deterministic controls, and guardrails that reduce hallucinations and prevent inappropriate autonomous behavior.

• Design observability and evaluation mechanisms that measure workflow completion, quality, accuracy, latency, cost, user satisfaction, and business impact.

End-to-End AI Solutions Engineering

• Take ownership of AI-enabled solutions from initial problem definition and process discovery through architecture, prototyping, testing, deployment, and user adoption.

• Rapidly convert loosely defined business requirements into functional applications, internal tools, automation workflows, dashboards, assistants, or agent-based systems.

• Use a pragmatic mix of low-code, no-code, AI-generated code, and traditional scripting to deliver the right level of speed, maintainability, and scalability.

• Build user interfaces, lightweight web applications, APIs, integration services, data pipelines, and workflow logic needed to support complete business solutions.

• Connect databases, documents, knowledge repositories, enterprise applications, email, collaboration platforms, CRM systems, service-management platforms, and external APIs to AI-powered workflows.

• Move successful prototypes into stable, secure, and supportable production environments with appropriate documentation, monitoring, testing, and ownership.

• Work with users to refine solutions based on real-world feedback and ensure that tools are adopted, trusted, and embedded into day-to-day operations.

Business Process and Workflow Architecture

• Analyze existing operational processes to identify repetitive work, decision bottlenecks, fragmented data, manual handoffs, and opportunities for intelligent automation.

• Decompose human workflows into clear algorithmic steps while preserving necessary judgment, context, and governance.

• Determine which workflow elements should be automated, AI-assisted, deterministic, manually reviewed, or excluded from automation.

• Create process maps, solution diagrams, data-flow models, agent responsibilities, and functional specifications that make complex systems understandable to business and technical stakeholders.

• Define measurable outcomes for each solution, including productivity gains, cycle-time reduction, service improvements, revenue impact, cost reduction, or risk mitigation.

Integration, Data and Technical Enablement

• Design and implement integrations using REST APIs, GraphQL, webhooks, event triggers, message queues, database connectors, and platform-specific automation capabilities.

• Work with structured and unstructured data from relational databases, spreadsheets, documents, email, knowledge bases, cloud storage, and third-party systems.

• Implement retrieval-augmented generation, semantic search, embeddings, vector stores, document ingestion, and structured output workflows where appropriate.

• Use Python, JavaScript or TypeScript, SQL, and shell scripting to extend platforms, transform data, troubleshoot integrations, and close gaps that cannot be addressed through no-code tools alone.

• Apply secure handling of credentials, authentication, authorization, sensitive data, model access, and external tool permissions.

• Collaborate with software engineering, data, security, IT, operations, and product teams to ensure solutions align with enterprise architecture and governance requirements.

Stakeholder Engagement and Adoption

• Partner with business leaders and functional teams to identify high-value AI use cases and convert operational needs into viable implementation plans.

• Lead discovery sessions, process-mapping workshops, technical demonstrations, pilot reviews, and solution handoffs.

• Communicate complex AI capabilities, limitations, risks, and tradeoffs in clear language for both technical and non-technical audiences.

• Set realistic expectations regarding model reliability, autonomy, data quality, security, implementation effort, and required human oversight.

• Develop user guidance, operating procedures, training materials, and adoption plans that help teams use new systems effectively.

• Act as an internal advisor on responsible and practical uses of generative AI, automation, and agentic technology.

Required Skills and Qualifications

• Demonstrated experience designing and delivering AI-enabled applications, intelligent workflows, automation platforms, or autonomous and semi-autonomous agent systems.

• Strong practical experience with multiple generative AI ecosystems, such as Claude, ChatGPT, Gemini, GitHub Copilot, Cursor, Codex, Claude Code, v0, or comparable tools.

• Experience using orchestration and automation technologies such as LangChain, LangGraph, CrewAI, AutoGen, Flowise, Make, n8n, Zapier, or comparable platforms.

• Ability to map ambiguous and complex business processes into structured workflows, decision trees, system components, and executable logic.

• Proficiency in prompt design, context engineering, tool calling, structured outputs, JSON schemas, validation logic, and model instruction design.

• Practical ability to read, assemble, debug, and modify code in Python, JavaScript or TypeScript, and SQL, including code generated through AI-assisted development tools.

• Experience integrating applications through APIs, webhooks, databases, identity services, collaboration platforms, CRM systems, email, and other business applications.

• Understanding of software delivery fundamentals, including environments, source control, testing, deployment, logging, monitoring, documentation, and production support.

• Strong product mindset and a demonstrated ability to focus on user outcomes rather than technology experimentation alone.

• Excellent written and verbal communication skills, with the ability to work effectively with executives, operational teams, engineers, and end users.

• Exceptional learning agility and a track record of rapidly mastering new technologies, platforms, and delivery approaches.

• Ability to work independently, prioritize competing opportunities, and move from concept to working solution with limited supervision.

Preferred Qualifications

• Background in software engineering, solutions architecture, product development, business systems, data engineering, process automation, or technology consulting.

• Experience building customer-facing or enterprise-grade AI products rather than only personal productivity automations or demonstrations.

• Familiarity with retrieval-augmented generation, vector databases, semantic search, knowledge graphs, model routing, and AI gateways.

• Experience with Model Context Protocol, tool servers, function calling, agent memory, and standardized AI integration patterns.

• Experience deploying applications in AWS, Microsoft Azure, Google Cloud Platform, Vercel, Replit, or comparable cloud and application-hosting environments.

• Understanding of AI security and governance topics, including prompt injection, data leakage, excessive agency, access control, auditability, privacy, and responsible AI.

• Experience measuring the operational and financial value of automation initiatives and prioritizing use cases based on impact, complexity, and risk.

• Experience supporting organizational adoption of new tools through documentation, enablement, stakeholder engagement, and change management.

Technical Areas of Interest

• Large language models and multimodal AI

• AI agents and multi-agent orchestration

• Claude, ChatGPT, Gemini, Codex, Claude Code and AI-assisted development environments

• Prompt design, context engineering and structured model outputs

• Agent-to-agent communication, planning, delegation and memory

• Human-in-the-loop workflows and approval systems

• Retrieval-augmented generation and semantic search

• APIs, webhooks and enterprise application integration

• Low-code and no-code automation platforms

• Python, JavaScript or TypeScript, SQL and lightweight application development

• Workflow engines, event-driven systems and business process automation

• AI evaluation, guardrails, observability and performance monitoring

• Cloud deployment, security and production operations

• Product discovery, process mapping and user adoption

Success in This Role

Success will be measured by the candidate's ability to:

• Turn complex or loosely defined business problems into clear, executable AI and automation architectures.

• Deliver working, adopted solutions rather than isolated demonstrations or experimental prototypes.

• Reduce manual effort, shorten cycle times, improve decision support, or create measurable new business capability.

• Select and combine the right tools without becoming unnecessarily dependent on a single vendor, model, or framework.

• Build agentic workflows that are useful and autonomous where appropriate, while remaining controlled, observable, and safe.

• Move quickly while maintaining sufficient attention to reliability, security, maintainability, and user experience.

• Communicate clearly with both technical and non-technical stakeholders and build confidence in the solutions delivered.

• Create reusable assets and patterns that increase the organization's overall capacity to develop AI-enabled systems.

Ideal Candidate Profile

You are a pragmatic builder who is energized by the pace of change in generative AI. You can explore a new platform in the morning, understand how it fits into a broader architecture, and rapidly apply it to a real operational problem. You are comfortable working across AI models, automation platforms, APIs, data, lightweight application code, and user workflows.

You do not treat AI as a substitute for sound system design. You understand that effective AI solutions require clear objectives, high-quality context, reliable integrations, validation, security, monitoring, and thoughtful human oversight. You know when to use an LLM, when to use deterministic logic, when to automate through a platform, and when a conventional software component is the better solution.

Most importantly, you are execution-oriented. You can move from discovery to prototype to production, communicate progress and tradeoffs clearly, and deliver tools that people trust and use.