Infra Software Engineer — AI Orchestration & Runtime

Normal Computing Corporation; New York (NY); On-site; USD 150,000 - 210,000; Full time

Job summary

Normal Computing is seeking an Infrastructure Software Engineer to build the production systems behind its AI products. You will own the runtime, orchestration, and internal APIs that support long-running workflows across distributed environments.

This role sits between product, AI, and platform engineering; you will ensure developer experience, observability, and reliability while turning promising prototypes into durable production systems that scale with the product.

Qualifications

• 4+ years of experience in infrastructure software, backend infra, production infra, platform engineering or distributed systems.
• Strong software engineering fundamentals across APIs, data modeling, concurrency, debugging and testing.
• Experience building or operating production services where reliability and observability matter.
• Practical experience with Docker and Kubernetes, including debugging containerized workloads and lifecycle issues.
• Comfort with persistence systems such as Postgres, Redis, object storage, or similar data stores.
• Experience building orchestration systems, job schedulers, workflows, sandboxes or distributed execution systems.
• Strong systems thinking: state machines, retries, queues, leases, scheduling, long-running workflows.
• Pragmatic mindset: know when to improve or delete abstractions and when to ship simple solutions.
• Ownership mindset: care about production-operable systems and usability for other engineers.

Responsibilities

• Runtime & Orchestration: Build and maintain production infrastructure for AI products, including orchestration, execution, and runtime systems.
• Internal APIs: Design backend services and APIs used by product engineers, AI engineers, and execution services.
• Operational Maturity: Improve state management, failure handling, metrics, tracing, and debugging tools.
• Execution Environments: Work with Kubernetes-backed environments, container lifecycle, scheduling, autoscaling, and isolation.
• Developer Experience: Build tools and abstractions to make systems easier to use and extend.
• Prototype-to-Production: Turn prototypes into durable production systems with scalable abstractions.
• Design Leadership: Lead discussions on API boundaries, state management, execution models, and tradeoffs.

Skills

Distributed systems

Backend programming

APIs

Debugging

Testing

Tools

Docker

Kubernetes

Postgres

Redis

Job description

Normal Computing is seeking an Infrastructure Software Engineer to build the production systems behind its AI products. You will own the runtime, orchestration, and internal APIs that support long-running workflows across distributed environments.

This role sits between product, AI, and platform engineering; you will ensure developer experience, observability, and reliability while turning promising prototypes into durable production systems that scale with the product.