Senior or Staff Software Engineer, Inference / Compute Infrastructure Engineering

Togetherai; Amsterdam; On-site; EUR 110,000 - 160,000; Full time

Job summary

Together AI, the AI Native Cloud, is building an infrastructure-as-software platform to transform hardware lifecycles into scalable AI clusters. This role develops the state machines, declarative control planes, and robust workflows that manage from bare metal to production-grade inference clusters.

You will own software that provisions, scales, and heals GPU-backed infrastructure, with a product mindset and production-grade CI/CD processes.

Qualifications

• Strong software engineering background in Go, Python, Rust, or similar.
• Experience with durable workflow orchestration tools such as Temporal, Cadence, or equivalent.
• Experience building software control planes or orchestration systems that model state and reconcile it over time.
• Experience with event-driven systems using message queues or pub/sub (Kafka, NATS, SQS).
• A product mindset with experience delivering internal platforms or APIs.

Responsibilities

• Build the provisioning state machine for full lifecycle of hardware, from discovery to decommission.
• Design a self-service API so the inference team can manage clusters with a single API call.
• Automate self-healing: detect degraded nodes, trigger repair, and reintroduce capacity.
• Own reliability of the pipeline with idempotency, retries, rollback, and drift detection.
• Collaborate with the inference/ML platform team to encode cluster shapes as abstractions.
• Engineer with strong typing, automated tests, code review, versioning, and CI/CD for infra code.

Skills

Go

Python

Rust

Temporal

Cadence

Kubernetes

Kafka

NATS

SQS

Product mindset

Tools

Temporal

Cadence

Kubernetes

Job description

About the Role

We're looking for a Software Engineer to build the systems that treat infrastructure as software. This role owns the software state machines that provision hardware, bring it into service, and manage its full lifecycle - turning racks of GPUs into running inference clusters without a human touching a runbook. The Research and Inference team is your customer: today they file tickets and wait; the target state is that they issue a single API call to stand up, scale, or tear down a cluster, and the system takes care of the rest. The platform is manifest-driven such that teams declare the desired state of a cluster or host - shape, topology, software stack - and the system is responsible for reconciling reality to that manifest, continuously, through every stage of its lifecycle. You will design the engines that manifest the schema, the engines that execute against it, and the workflows that carry a piece of hardware or a cluster from one state to the next—taking it from bare metal to a fully functioning AI cluster for training or inference. You'll write production code which is typed, tested, versioned, and deployed through CI/CD that models infrastructure state and reconciles it, the same way a Kubernetes controller reconciles a cluster's desired state. Success looks like eliminating manual provisioning work, not documenting it better. A product mindset - you've built internal platforms or APIs consumed by other engineering teams and care about the developer experience of what you ship. You build it, you own it. You are not only responsible for delivering the software but also for operating and supporting it in production.

Responsibilities

• Build the provisioning state machine: design and implement the software that models the full lifecycle of a physical host from discovery, inference bring-up to GPU driver/CUDA stack, health validation, and decommission/RMA — as explicit, versioned states and transitions.
• Build the self-service API: design declarative APIs and a control plane so the inference team can request, scale, and tear down inference clusters with one API call — no ticket, no human in the loop.
• Automate self-healing: detect degraded or failed nodes, drain them safely, trigger repair or replacement, and reintroduce healthy capacity into the pool automatically.
• Own reliability of the pipeline: idempotency, retries, rollback, and drift detection so the provisioning system is as dependable as any other production service.
• Partner with the inference/ML platform team: understand the cluster shapes they need — topology, interconnect, scheduling constraints — and encode them as first‑class abstractions in the platform.
• Engineer it like software: strong typing, automated tests, code review, versioning, and CI/CD for infrastructure code — this is a product, not a collection of Ansible playbooks.

Requirements

• Core requirements (all levels): Strong software engineering background in Go, Python, Rust, or similar — you write and test real software for a living.
• Experience with durable workflow orchestration tools such as Temporal, Cadence, or equivalent to run long‑lived, manifest‑driven workflows that survive failures and resume mid‑execution.
• Experience building software control planes or orchestration systems that model state and reconcile it over time (e.g., Kubernetes controllers/operators, custom reconciliation loops, workflow engines).
• Experience with event‑driven systems — designing and building software around message queues, event streams, or pub/sub (e.g., Kafka, NATS, SQS) rather than polling or cron‑driven scripts.
• A product mindset. You’ve built internal platforms or APIs consumed by other engineering teams and care about the developer experience of what you ship.

Nice to have

• Exposure to bare‑metal provisioning (PXE/iPXE, Redfish/IPMI, BMC) and/or networking fundamentals (VLANs, BGP, fabric design), or GPU/accelerator infrastructure.
• Experience with GPU cluster software stacks (NCCL, CUDA, InfiniBand/RoCE).
• Prior work at a hyperscaler, GPU cloud, or datacenter‑scale infrastructure organization.
• Systems programming in Rust or Go.

About Together AI

Together AI, the AI Native Cloud, is purpose‑built for AI engineers. AI application developers get high‑performance inference that scales reliably, fine‑tuning and reinforcement learning for creating frontier‑level specialized models, and pre‑training at massive scale for fully custom intelligence, all around a marketplace of leading open models that teams can run, adapt, and own. Trusted by Cursor, Decagon, ElevenLabs, Salesforce, and Zoom, Together serves 400+ trillion tokens a month.

Equal Opportunity Together AI is an Equal Opportunity Employer and is proud to offer equal employment opportunity to everyone regardless of race, color, ancestry, religion, sex, national origin, sexual orientation, age, citizenship, marital status, disability, gender identity, veteran status, and more.

Please see our privacy policy at…