Lead AI/Agent Architect

Future Works

Lead AI/Agent Architect at Future Works designing AI agent systems for complex workflows. Building operational AI for high footprint companies in energy, real estate, data and beyond.

Posted 7/9/2026contractRemote • 🇬🇧 United KingdomSeniorWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates expertise in designing and architecting agent systems, with a strong focus on end-to-end solutions, compliance, and governance in high-stakes environments. Proficient in Python, API design, and transitioning systems from sandbox to production while ensuring auditability and traceability.

Highest-signal resume keywords

Agent Systems ExpertiseExpert Python ProgrammingHuman-in-the-Loop DesignPath to Production ExperienceDomain Knowledge in Financial Services

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

Agent OrchestrationTool and Function CallingState ManagementAPI DesignTyped Tool DesignPostgreSQLData Pipeline DesignModel Services IntegrationBusiness Logic DevelopmentUser-Facing Application Design

Soft Skills

Agile ExecutionSystems Thinking

Tools & Technologies

LLM Code AssistantsSandbox EnvironmentsData Governance Tools

Industry Keywords

Commercial Real EstateLegalFinancial ServicesDocument-Driven TransactionsAuditabilityTraceability

Tech Stack

Tools & technologies

PostgresPython

About the role

Key responsibilities & impact

As the Lead AI/Agent Architect, you own the technical track.
You will design the agent orchestration model, the tool-use architecture, and the human-in-the-loop protocol, and you will stand up the secure sandbox environment the system runs against.
You will turn a fragmented, document-heavy operational workflow into a secure, auditable, and extensible agent system, and you will validate exactly where automation ends and expert judgment begins.
You are accountable for an architecture that processes a live transaction scenario end to end with human intervention only at documented gates, and that extends to adjacent workflows without a rebuild.
Own the orchestrator agent that holds the deal state machine and routes work to one specialist agent per stage, defining stage handoff protocols and cross-stage integration.
Design the typed tool layer as the integration seam that binds to sample data in the sandbox and to live systems in production, so the move to production is a connector change rather than a rebuild.
Define the mandatory approval gates and review checkpoints, ensuring the agent never executes binding legal or financial actions without broker confirmation.
Own the sandbox data model and test scenarios, and define the security, compliance, and data-governance approach.

Requirements

What you’ll need

8+ years in software engineering, AI/ML, or solutions architecture, with a strong track record of designing and shipping production-grade systems, and recent hands-on experience architecting LLM or multi-agent systems.
Agent Systems Expertise: Deep, hands-on experience with agent orchestration, tool and function calling, state management, and retrieval, ideally in production rather than prototypes.
Technical Breadth: Expert Python (or equivalent), API and connector design, typed tool and interface design, and modern data stores such as PostgreSQL.
Systems Thinking: Proven ability to design end-to-end solutions connecting data pipelines, model services, business logic, and user-facing applications under real operational constraints.
Human-in-the-Loop & Governance: Experience designing guardrails, approval gates, auditability, and traceability for high-stakes, document-heavy domains where decisions must be explainable and reviewable.
Domain Knowledge: Previous experience in commercial real estate, legal, financial services, or another structured, document-driven transaction domain is highly preferred.
Path to Production: Practical experience taking a sandbox or prototype system to production through connector and tool abstraction, including performance, monitoring, deployment, and rollback.
AI-Native Workflow: Comfort utilizing LLM code assistants and agentic engineering to improve speed, quality, and architectural clarity.
Agile Execution: Ability to work effectively in fast, hypothesis-driven delivery cycles where the focus is on proving value quickly without creating unnecessary technical debt.

Benefits

Comp & perks

Work from anywhere, forever - We are a fully remote and global team. We trust you to manage your time and energy to deliver exceptional results.
Connect deeply - We gather for immersive, all-expenses-paid company retreats in unique locations to connect, learn, and grow together.
Share in the upside - A competitive compensation package including equity, bonuses, substantial participation in company profits with a clear growth path to C-Level leadership based on performance.