I

Inworld AI

Real-time AI NPC engine for gaming

Staff / Principal Software Engineer - Inference Platform

Backend EngineeringConfirmed live in the last 24 hours
Full-timeMountain View, CA, USA

About the Job

Requirements

  • At least 8 years of experience building backend or distributed systems using Go, Rust, Java, or C++.
  • Experience designing and shipping a multi-service system end to end, and explaining its trade-offs and production failures.
  • Deep understanding of distributed systems, including consistency, failure modes, queuing, load balancing, and capacity modelling.
  • Experience building a platform or developer product with external customers, such as cloud compute, PaaS, serverless, or an API platform.
  • Ability to produce clear technical writing and turn an ambiguous problem into a design document that others can build from.
  • Candidates must be based in the San Francisco Bay Area or willing to relocate.

Responsibilities

  • Design and build the platform's core services, including the control plane, model and deployment lifecycle APIs, tenant isolation, metering, and quotas.
  • Own GPU capacity allocation and scheduling across shared and reserved workloads, balancing latency, cost, and reliability.
  • Build the process that takes a customer's model from weights to production serving and keeps it healthy as it changes.
  • Write production code, mostly in Go, every week, shipping services rather than only configuring them.
  • Define APIs and abstractions for customers and internal teams to build on, making the right path the easy path.
  • Lead design reviews, write the platform's technical direction, and raise the bar for system design across engineering.
  • Operate the systems built by setting SLOs, participating in incidents, and turning postmortems into design changes.

Desired Qualifications

  • Experience with schedulers or resource managers for scarce hardware, such as GPU clusters, batch systems, or cloud compute.
  • Experience with LLM inference serving tools such as vLLM, SGLang, or TensorRT-LLM, or with ML training infrastructure.
  • Experience with multi-tenant systems that use usage-based billing or contractual SLAs.
  • Familiarity with Kubernetes, Terraform, and GitOps such as ArgoCD.

About the Company

Inworld AI

Real-time AI NPC engine for gaming

Inworld AI builds AI-powered non-player characters (NPCs) for games. It offers a real-time character engine that delivers low-latency, scalable interactions, along with tools for safety, knowledge, memory, narrative control, and multimodal capabilities. The NPCs have distinct personalities and emotional intelligence, can learn and recall past interactions, and autonomously pursue goals integrated into gameplay. The company targets game developers, selling access to its engine to create believable autonomous characters that enhance storytelling and player immersion at scale.

Company size
51-200
Company stage
Series A
Total funding
$117M
Headquarters
Mountain View, CA
Founded
2021

Recently Posted Jobs

Explore more opportunities at Inworld AI

See more jobs