Job Description

Roles & Responsibilities

Define platform architecture: modular components, data contracts, integration patterns, deployment topology (cloud/on-prem), and security/observability standards.

Design reusable platform primitives : canonical entities (resources/tasks/time/cost), constraint packs, objective templates, scenario manager, and explainability layer.

Make solver/stack decisions (build vs buy), and establish technical roadmaps with the CTO.

Lead modeling and solution strategy for key families:

Production planning & scheduling (sequence-dependent setups/changeovers, minimum run lengths, maintenance windows)
Workforce allocation and shift planning
Routing, dispatching, and fleet assignment
Inventory/replenishment and supply chain planning

Set standards for model formulation, performance, scalability, and stability (runtime budgets, warm starts, decomposition, heuristics/hybrids where needed).

Build a repeatable benchmarking harness and KPI framework (cost, service, risk, feasibility rate, runtime).

Own the approach to infeasibility detection and repair (constraint relaxation strategies, IIS where applicable, actionable diagnostics).

Ensure decisions are explainable to operations teams (constraints hit, trade-offs, what changed vs previous plan, reason codes).

Partner with PM/Delivery to define scope, milestones, acceptance criteria, and technical risk management.

Guide integrations with ERP/WMS/TMS/CMMS/SCADA and production data pipelines.

Establish OptOps practices: versioning, monitoring, runtime regressions, rollback, and quality gates.

Mentor AI engineers (including those coming from NLP/CV backgrounds) into OR/Optimization craftsmanship.

Run architecture reviews, ADRs, and enforce best practices across code, models, and deployments.

7+ years in applied optimization / operations research / decision intelligence, with hands-on delivery experience.

Strong track record in building and deploying optimization systems using one or more of:

MILP / MIP, CP/CP-SAT, decomposition, heuristics/metaheuristics, hybrid strategies.

Ability to translate real operations into formal models (capacities, time windows, setup/changeover, batching, minimum run lengths, resource calendars, SLAs).

Solid software engineering fundamentals for production systems (clean architecture, testing, CI/CD mindset, performance profiling).

Experience integrating decision engines into real enterprise environments (APIs, event-driven patterns, data pipelines, on-prem constraints).

Clear communication: can explain complex trade-offs to both engineers and operators.

Hands-on experience in: OR-Tools (CP-SAT), Gurobi/CPLEX, Pyomo, JuMP, or similar.

Experience with feasibility diagnostics (IIS, relaxation, reason codes, repair recommendations).

Experience in building re-optimization loops (daily/shift updates, warm starts, rolling-horizon planning).

Observability/monitoring: Prometheus/Grafana (or equivalent), structured logging, runtime regression monitoring.

Preferred to have domain exposure in manufacturing planning, logistics routing, retail replenishment, or supply chain optimization.

Desired Candidate Profile