You will build and scale our batched inference platform, a distributed system that handles thousands of concurrent batch jobs across multiple LLM deployments.

Tech stack

• Rust for core services
• TypeScript for user interfaces
• PostgreSQL for persistent state
• Kubernetes for deployment and orchestration

Core areas of work

• Database optimization under high load and concurrent access patterns
• Distributed job scheduling and retry logic
• Real time observability and monitoring
• Designing for failure from the start to build reliability into the system

Requirements

Technically exceptional — Your skills span domains and technologies. You solve genuinely hard problems and have consistently demonstrated this.

Distributed systems experience — You have delivered distributed systems in production. You understand high throughput, highly parallel architectures and can point to concrete examples of excellent work.

Pragmatic shipper — You move fast while maintaining stability for a large user base.

Humble — You lead by example. You take accountability quickly and say "I don't know" when appropriate.

Customer focused — You start from real user problems and deliver technical solutions. You are a problem solver, not a technology purist.

Nice to have

• Experience with our stack: Rust, TypeScript, PostgreSQL, Kubernetes
• Experience with LLM inference systems or batch processing infrastructure

• We are technically ambitious. Hard problems energize us.
• We move fast. Priorities shift and requirements evolve. You should be excited by rapid iteration.
• We choose pragmatic solutions over clever ones. The right answer beats the interesting answer.
• We operate in ambiguity. Decisions are made with incomplete information and revised when evidence changes.

Technical Culture Interview — 30 minute video call with an engineer. We discuss your experience and alignment with our engineering culture.

Wider Culture Interview — 30 minute video call with someone outside the tech team. This focuses on company values and how you work with others.

Technical Design Interview — 1 hour video call with members of the engineering team. We present a challenge and collaboratively design a system.

Paid Day Work Trial — Spend a day working on a real problem from our Batched Inference Server. This gives you a genuine sense of how we operate, and gives us insight into how you approach real world problems. Compensation: $1,000.

Offer — If there is strong mutual alignment, we make an offer and you join us on the journey.

Email your CV and a short note explaining why this role interests you to careers@doubleword.ai