Job Opportunities API

ABOUT FUTURE WORKS Future Works is a US-focused, AI-native professional services firm building operational AI and data systems. Our foundation beliefs are simple: optimization lowers need for resources, which increases sustainability and resilience. We are a team of "Time Benders" on a mission to collapse timelines to operational transformation of high footprint companies in energy, real estate, data and beyond. Together, we master velocity. We achieve our mission by building flawless, AI-powered systems. Our technology is already far more advanced than that of boutique services firms, but we are only getting started and the road from here leads to becoming world's best Service-as-Software company. Regardless of the specific role, our ideal candidate will always have a keen interest in building symbiotic human-AI systems both individually and for teams; high energy, high agency and a certain passion for bending time.   THE ROLE We are running an engagement to design and build an AI agent system that manages a complex, high-value transaction workflow for a large enterprise client, from initial engagement through close-out, across a multi-stage process. 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. Working closely with AI/ML Engineers, a Lead Business Analyst, and the Engagement Director, 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.   KEY RESPONSIBILITIES - Agent Orchestration Design: 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. - Tool-Use Architecture: Design the typed tool layer (template population, market-data query, financial analytics, clause extraction, document assembly) 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. - Human-in-the-Loop Protocol: Define the mandatory approval gates (engagement agreement issuance, LOI execution, lease signature, invoice issuance) and review checkpoints (requirements-brief sign-off, short-list, negotiation positioning), ensuring the agent never executes binding legal or financial actions without broker confirmation. - Secure Sandbox & Data Governance: Own the sandbox data model and test scenarios, and define the security, compliance, and data-governance approach: data residency, PII handling, audit logging, and a zero-retention policy with no training on client or deal data. - Feasibility Validation: Validate the technical feasibility of the automation hypotheses stage by stage and translate the automation boundary findings into architecture. - Extensibility by Design: Architect the system with explicit extensibility to Agency (Landlord Rep) workflow and other brokerage lines, producing a platform foundation rather than a point solution. - Cross-Functional Technical Leadership: Lead and direct the AI/ML Engineers through the build phases, managing orchestration and cross-stage integration while engineers build per-stage capabilities in parallel.   WHAT WE'RE LOOKING FOR REQUIRED SKILLS AND EXPERIENCE - 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