Agentic Orchestration Lead

PRISM; Gurugram District; Remote; INR 4,000,000 - 6,000,000; Full time

Job summary

PRISM OYO is seeking a senior engineering lead to build an autonomous operations platform that runs the back office for a global hospitality network. You will design a platform substrate with identity, permissions, and an action-authority matrix, then enable live operations for properties worldwide.

The role focuses on end-to-end automation, lean governance, and scalable, auditable actions across multiple domains, including finance, payroll, and compliance.

Qualifications

• Shipped a production system that took consequential actions autonomously — money, inventory, or customer-facing — not just advisory.
• Built a workflow/case system with SLA-driven follow-up and escalation across human teams.
• Designed human-in-the-loop approval tiers and clean escalation handoffs.
• Built eval and observability for non-deterministic / agentic systems.
• Integrated against messy, flaky third-party APIs at scale.

Responsibilities

• Build the platform substrate: identity, permissions, and the action-authority matrix.
• Integrate with PMS, ERP/accounting, payroll, banking, tax portals, ticketing, messaging.
• Create the case + closure engine — opens a task, assigns it, chases it, verifies, and closes.
• Implement escalation routing with SLA ladders and audit logging.
• Develop per-jurisdiction policy/knowledge packs and a live ops heartbeat per property.
• Pilot the first live tenant: the operations heartbeat and autonomous actions.

Skills

Autonomous systems

Workflow automation

SLA-driven escalation

Observability

APIs integration

Job description

PRISM OYO, a global leader in hospitality technology, operates across 35+ countries with a diverse portfolio of brands and offerings. Its key subsidiaries include OYO Vacation Homes, featuring brands like DanCenter, Belvilla, and Directbooker in Europe; Motel 6 in the U.S.; Sunday, a premium luxury brand with a global footprint; and Townhouse, a premium value brand operating worldwide.

Expanding its portfolio to encompass Hotels, Vacation Homes, and Workspaces, OYO manages renowned brands like OYO Hotels, Sunday, Innov8, Motel 6, Check My Guest, Belvilla, DanCenter, and Traum-Ferienwohnungen. Since its inception in 2013, OYO has become one of the world's fastest-growing hotel networks, overseeing 174K+ hotels and homes with 250K+ rooms globally. Its operations span the USA, Latin America, Europe, India, China, Japan, Malaysia, the UAE, Indonesia, and the UK.

As one of the few Indian startups achieving profitability, OYO boasts an EBIDTA of $100 million and aims for tenfold growth within the next five years.

Compensation is competitive cash plus a meaningful equity stake appropriate to a founding technical hire.

About the Role

Agentic Orchestration Lead — Autonomous Operations Platform Location: India (Bengaluru / Gurugram / remote-India) Reports to: Group Head of Technology Team: Founding hire. Builds the platform, then a small team of 2–4 strong ICs.

Responsibilities

The mission

• Build an always-on software system that runs the back office of a global hospitality platform— sensing the state of every property and every corporate workflow, deciding what needs to happen, acting within bounded authority, and driving each task to verified closure across the responsible human teams, escalating only true exceptions.
• You are not building a chatbot or a dashboard. You are building an agent platform: a shared substrate on which the first agent (live hotel operations) is the reference implementation, and onto which finance, payroll, tax, safety, and every other corporate function plug in over time as policy + tools, not as new from-scratch builds.
• The end state is a thin control tower — a small number of controllers, approvers, and exception handlers — in place of large HQ processing teams. Routine work runs itself; humans own judgment, approvals, and statutory sign-off.

What you will build

• The platform substrate (build once, every agent reuses):
• Identity, permissions, and the action-authority matrix
• Integration/tool layer to the operational stack (PMS, ERP/accounting, payroll, banking, tax portals, ticketing, messaging)
• The case + closure engine — opens a task, assigns it, chases it, verifies the work actually happened, and only then closes
• Escalation and approval routing with SLA ladders
• Eval, audit log, and observability for non-deterministic actions
• Per-jurisdiction policy/knowledge packs
• The first tenant — live operations heartbeat: an event-triggered + scheduled loop that, per property, continuously senses state (occupancy, OOO rooms, pricing signals, guest messages, housekeeping, maintenance, compliance) and runs it to closure across the responsible teams.
• The path to a fleet: the platform makes each subsequent agent (AP, AR, reconciliations, health & safety, security, payroll, tax) mostly config + policy + eval, shipping faster as the substrate hardens.

What you will own

• The action-authority tiers (autonomous / notify-after / approve-before / human executes-statutory) and the guardrails that keep every action inside them.
• Closure verification — proving a task is actually done, not just marked done.
• Reliability of consequential, non-deterministic actions: idempotency, dry-run, rollback.
• The eval harness and audit trail that make the system trustworthy and auditor-legible.
• Cost-per-decision economics at the scale of thousands of properties.

The hard problems (the seniority filter)

• Closure verification. The single hardest part. How do you know the room was actually re-cleaned, the ticket actually resolved, the invoice actually matched — not just stamped done?
• Bounded autonomy. Designing an authority matrix that auto-acts on the reversible and routes the irreversible to a human, with no gaps.
• Action safety. Never double-charge, double-message, or double-file. Idempotency and rollback on everything that touches money, inventory, or a guest.
• Eval before execution. Catching a wrong or hallucinated action before it fires.
• Frontline trust. GMs and staff must lean on it, not route around it.
• Multi-jurisdiction. 35+ countries means “taxation” or “payroll” is a framework plus per country policy packs, never a single agent.

Success looks like

• 90 days: platform substrate stood up; operations heartbeat live on a pilot cluster doing sense + detect + a handful of autonomous actions; full audit log.
• 180 days: closed-loop on a defined operations case set (OOO, housekeeping, guest message SLA, rate band) with verified closure and working escalation; measurable drop in human touches and SLA breaches.
• 365 days: majority of routine operations cases handled end-to-end with humans only on exceptions; second-wave agents (AP, AR, H&S, security) shipping on the same platform; eval harness mature.

What this role is NOT

• Not building a small/domain language model yet — that is a later phase, trained on the data this platform generates.
• Not rebuilding the PMS or the guest product.
• Not a research role. This ships to production under real reliability constraints.

How we work

• You’ll partner with central operations, finance, and the regional ops leadership, and later with domain owners (finance controller, payroll/comp lead) who supply policy and own approvals.

Qualifications

None specified.

Required Skills

Must-haves (proof, not potential)

• Shipped a production system that took consequential actions autonomously — money, inventory, or customer-facing — not an advisory tool.
• Built a workflow/case system with SLA-driven follow-up and escalation across human teams (real-time ops automation at a delivery, logistics, fintech, QSR-chain, or marketplace company is the closest analog).
• Designed human-in-the-loop approval tiers and clean escalation handoffs.
• Built eval and observability for non-deterministic / agentic systems.
• Integrated against messy, flaky third-party APIs at scale.