Spatial Support is hiring a Senior Backend & LLM Orchestration Lead to own the AI backend behind our 3D product experiences. You’ll level up our Python/FastAPI services and streaming-first LLM pipelines (LangChain/LangGraph or custom) to deliver sub-second, scene-aware answers. You’ll design secure, multi-tenant APIs and websockets, build on GCP (Cloud Run/Functions, Pub/Sub), and drive observability, CI/CD, and IaC. Expect async and GPU-heavy workloads, PostgreSQL + Redis, and tight collaboration with 3D/ML to expose object recognition and spatial reasoning via clean APIs. You bring 5+ years in production backends, strong auth/security chops, and a knack for debugging distributed systems. Bonus: RAG/agents, 3D/CAD exposure, Terraform/GitHub Actions. Remote-first, APAC-friendly. Help set the standard for instant, reliable, context-rich AI.

Senior Backend & LLM Orchestration Lead (Python/LangGraph, GCP)

APAC-Singapore HQ
Hybrid
Apply

Senior Backend & LLM Orchestration Lead

About the role
Own the core AI backend that powers Spatial Support’s 3D product experiences. You’ll lead our Python/FastAPI orchestration layer that fuses large language models with scene context from complex 3D assets—delivering secure, streaming-first responses with sub-second latency on Google Cloud.

Your first 90 days

  • Audit and elevate our LLM orchestration pipeline (e.g., LangChain/LangGraph or custom flows) to streaming-first performance.
  • Establish clear SLOs for p50/p95 latency, reliability, and throughput; ship improvements fast.
  • Harden our auth-first, multi-tenant architecture across APIs and websockets.
  • Stand up actionable observability: structured logs, distributed tracing, and alerting dashboards.

What you’ll do

  • Design, build, and operate backend services that orchestrate multi-step LLM workflows and retrieve 3D/scene context in real time.
  • Optimize asynchronous execution, streaming responses, and GPU/compute utilization for low latency and high throughput.
  • Enforce secure authentication and authorization end-to-end; keep tokens, access control, and data boundaries tight.
  • Run our stack on GCP (e.g., Cloud Run/Functions, Pub/Sub, managed DBs); streamline CI/CD and IaC for rapid, reliable releases.
  • Define and monitor key metrics (latency, error rates, QPS); use data to prioritize fixes and performance work.
  • Partner with 3D and ML engineers to expose new capabilities (object recognition, scene awareness) as robust APIs.

What you’ll bring

  • 5+ years building production backends in Python (FastAPI/Flask or similar); you’ve shipped clean REST and streaming APIs.
  • Hands-on experience with LLMs or data-heavy systems; familiarity with orchestration frameworks or custom agent pipelines.
  • Strong security fundamentals: OAuth2/JWT, access control, encryption, and secure multi-tenant design.
  • Cloud ops proficiency (preferably GCP) plus Docker, CI/CD, and infrastructure-as-code.
  • Depth with PostgreSQL and Redis: data modeling, query optimization, and caching for high-traffic services.
  • Excellent debugging in distributed, async systems; you profile, trace, and fix bottlenecks methodically.

Bonus points

  • Production experience with RAG, tool-using agents, or multi-step decision flows.
  • Exposure to 3D/spatial data (game engines, CAD/BIM, AR/VR).
  • DevOps automation (Terraform, GitHub Actions) and modern monitoring stacks.
  • Mentorship or tech leadership in small teams; setting standards via reviews and architecture docs.
  • OSS contributions, talks, or writing on backend/AI orchestration.

Why this role matters
The backend is the brain and heartbeat of our product. Your work makes our AI feel instant, reliable, and context-aware—turning complex CAD into a seamless, support-rich 3D experience. As we push toward our 2026 ambitions, you’ll help set a new standard for AI-driven support.

How we work
Remote-first and APAC-friendly. We collaborate primarily on Singapore time (GMT+8) and aim for ~4 hours of overlap on weekdays. Interested? We’d love to hear from you.

‍

Apply