Principal Platform Engineer - Real-Time AI Inference (Go)

BITKRAFT Ventures; Mountain View (CA); On-site; USD 280,000 - 350,000; Full time

Job summary

Inworld is seeking a Staff or Principal Software Engineer to design and implement the core architecture of our Inference platform. You will own the production system that serves tens of trillions of tokens monthly, shaping abstractions and APIs used by customers and internal teams.

You will write substantial production Go code, optimize scheduling of GPUs across tenants, and partner with research, product, and leadership to define the platform's future.

Qualifications

• 8+ years building backend or distributed systems in Go, Rust, Java or C++.
• Experience shipping a multi-service system end to end and explaining trade-offs.
• Clear technical writing to document designs and decisions.

Responsibilities

• Design and build the platform's core services: control plane, APIs, and tenancy.
• Own GPU capacity scheduling and latency/cost trade-offs.
• Lead the path from weights to production serving and maintain health during changes.
• Write production code, primarily in Go, shipping services.
• Define APIs and abstractions for customers and internal teams.

Skills

Backend development

Distributed systems

Go

Rust

Java

C++

Technical writing

Education

Bachelor's degree in Computer Science or related field

Tools

Kubernetes

Terraform

ArgoCD

Git

Job description

Inworld is seeking a Staff or Principal Software Engineer to design and implement the core architecture of our Inference platform. You will own the production system that serves tens of trillions of tokens monthly, shaping abstractions and APIs used by customers and internal teams.

You will write substantial production Go code, optimize scheduling of GPUs across tenants, and partner with research, product, and leadership to define the platform's future.