Senior Backend & LLM Orchestration Lead - Fulltime - East Asia/ EMEA

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!