DevOps / Infrastructure Engineer

$210k - $240k + equity

Location
New York
Workplace
On-site
Employment
Full-time
Visa
No Visa Sponsorship

About this role

We are looking for a DevOps / Infrastructure Engineer with 4-7 years of experience to set up the infrastructure foundation across our API, the backend behind it, and model serving. We need someone who has built those things: someone who has set up infrastructure for a new product or feature, not only operated one someone else built. We're early, and the infrastructure foundation is yours to set up. Every service needs a reliable path from commit to staging to production, and every failure needs to show up on a dashboard or in an alert before a customer notices.

What will you be doing?

Kubernetes from the start. Setting up the cluster, workloads, and configuration we'll run on as traffic and the number of services grow.

Staging that matches production. A staging environment close enough to production that what passes there works in prod.

Deploys that are safe and boring. Pipelines that build, test, and ship every service, with rollbacks that work.

Seeing everything. Monitoring, logging, and tracing across the API, backend, and serving layer, so we know what's slow or broken and why.

Alerts people trust. Error alerting and dashboards that page on real problems and stay quiet otherwise.

Apply to ScaleDown

They hire through Clera: your intro goes straight to the hiring team.

How it works

Confirm the fit

A few questions to make sure this role is the right shape for you. Two minutes.

Clera pitches you to the company

Clera writes the intro, sends it to the founder, and handles the back-and-forth.

A meeting lands on your calendar

When the company wants to meet, Clera gets the call on your calendar. You just show up.

Not the right role?

Ask your AI about this role

It knows you. Clera gives it the role.

Does this role fit my profile?

First time? Connect Clera once, about a minute.
One click above pre-fills the connector. Or by hand: Settings > Connectors > Add custom connector, paste https://mcp.getclera.com. Either way, sign in with the account you use on Clera and approve the consent screen.
https://mcp.getclera.com

Sign in with your Clera account. MCP docs

About ScaleDown

ScaleDown is an AI research lab building constrained decoding models that are 200x faster and 467x cheaper than traditional LLMs, with self-serve access through major platforms like OpenRouter and Vercel.

Team size
1-10 people
Founded
2024
Industry
AI
Workplace
On-site
Locations
New York, United States
Open roles
4

Know someone who'd fit?

Earn $5,000 per hire

Benefits

  • Early equity offered to employees

Culture & values

  • New hires work with Neal (CEO) every day and with Soham (CTO) on anything technical
  • Team works on-site in NYC and expects to grind a lot
  • Monthly launches on X, fast-moving benchmarks, and content that ships quickly
  • Neal wants everyone who joins ScaleDown to eventually start their own company
  • Team members get a view into how the whole business runs, including fundraising, partnerships and go-to-market
  • Team values sharp, curious people with hot takes on AI and the model layer
  • A little weirdness is welcome, including humor and memes for developers
  • Team works directly with engineers and marketers at partners like OpenRouter and LangChain
  • Team hosts developer happy hours, research paper readings and research dinners in NYC
  • Engineers build with coding agents every day