InfrastructureFull-time

Platform Reliability Engineer (SRE)

Keep one endpoint dependable across a churning set of upstream providers: failover, rate-limit absorption, and the spend caps that fail closed.

You will keep Direct Inference dependable while the model market, providers, customer traffic, and production workloads keep changing underneath it.

Apply for this role See all roles

About Direct Inference

Direct Inference is the endpoint that does everything frontier models can do. Customers bring the SDK and model id they already use; Direct Inference handles capability, quality, cost, latency, failover, and provider churn behind the scenes.

The important product constraint is zero-knowledge: customers never see which model, provider, or version served a request. That lets them build on a stable surface while the model market keeps moving underneath it.

What you'll own

Own production reliability across deploys, health checks, alerting, incident response, and post-incident hardening.
Build provider-health automation and capacity controls that keep customer workloads served through upstream instability.
Improve fail-closed spend controls, abuse handling, and runaway workload protection.
Harden observability for latency, error rate, cost, saturation, and customer-impact analysis.
Partner with inference engineering on fallback behavior and with product engineering on operator-facing reliability views.
Write runbooks, tests, and automation that make production operations repeatable.

Projects you might ship

Improve provider-health monitoring so the system can react faster to degraded upstream paths.
Harden the deploy and verification loop so releases can be proven from workflow, running image, healthcheck, and production state.
Build a capacity or spend-control guardrail that prevents one customer, provider event, or runaway workload from affecting everyone else.

What we're looking for

You have operated production systems with real uptime, latency, or financial consequences.
You are comfortable debugging across application code, infrastructure, networking, deploy tooling, logs, and metrics.
You know how to design alerts and runbooks that help during incidents instead of adding noise.
You can automate recurring operational work without losing sight of the customer impact.
You care about reliability as product quality, not just infrastructure hygiene.

Nice to have

Experience operating API infrastructure, model-serving systems, payment/billing paths, or high-traffic developer platforms.
Comfort with incident command, postmortems, SLOs, tracing, metrics, and alert design.
A bias toward simple operational tools that make the right thing easy during pressure.

Your first 90 days

Own one reliability improvement from production signal to deployed fix.
Improve a runbook, alert, or health check so incidents get clearer and shorter.
Build a concrete capacity, provider-health, or spend-control hardening project.

Benefits & support

Built for people doing serious work in a small team.

Competitive salary and meaningful equity

Remote-first work with San Francisco collaboration space

Medical, dental, and vision coverage

Home-office and developer-tooling budget

Quarterly team working sessions and offsites

Direct access to customers and production product decisions

Interview process

A direct loop with the people doing the work.

01

Intro

A focused conversation about your background, what you want to build, and where this role should create leverage.

02

Technical

A practical working session around the kind of problem this role owns. We prefer realistic systems over puzzle interviews.

03

Team

Meet the people you would work with across product, engineering, reliability, and customer-facing work.

04

Offer

We align on scope, compensation, start timing, and the first problems you would take on.

Application

Apply for Platform Reliability Engineer (SRE).

Share the practical context we should know before the first conversation. We read applications for ownership, clarity, and evidence of shipped work.

First name *Last name *Email *PhoneLocation *Remote work locationLinkedInWebsite, GitHub, or portfolioResumeUpload PDF, DOC, or DOCXWhy this role?How did you hear about us?Are you authorized to work where you are based? *Will you now or later require visa sponsorship? *

Voluntary self-identification

These questions are optional and never affect hiring decisions. Choose “Prefer not to say” anywhere you would rather not answer.

GenderRace / ethnicityVeteran statusDisability status

I certify that the information in this application is accurate to the best of my knowledge.I consent to Direct Inference using my application information for recruiting and hiring purposes.

Required fields are marked with an asterisk.

Candidate notices

Equal opportunity

Direct Inference is an equal-opportunity employer. Qualified applicants are considered without regard to race, color, religion, sex, gender identity or expression, sexual orientation, national origin, disability, veteran status, age, or any other status protected by law.

Reasonable accommodations

If you need an accommodation during the interview process, contact careers@directinference.com. We will work with you on a reasonable path through the process.

Candidate privacy

Application information is used for recruiting, evaluation, coordination, and hiring operations. Access is limited to people involved in the hiring process and retained only as needed for legitimate recruiting and compliance purposes.

Compensation

Posted ranges are good-faith estimates for the role and may vary by experience, location, scope, and market conditions. Equity and benefits are considered as part of the total offer.

Work authorization

Candidates are asked about current and future work authorization so we can understand employment feasibility early. A sponsorship need does not automatically disqualify a candidate.

Recruiting safety

Direct Inference will not ask candidates to purchase equipment, send money, or share sensitive personal information before a formal process. Messages should come from a directinference.com address.

More openings

Other ways to build Direct Inference.

All roles

Forward Deployed Engineer

Engineering · Remote / San Francisco, CA

Work directly with high-intent customers to get production AI workloads running on Direct Inference, then bring the sharp edges back into the product and serving engine.

Senior Inference Engineer

Engineering · Remote / San Francisco

Own and extend the serving engine: the quality, latency, health, and price signals that decide how every request is served.

Full Stack Engineer

Engineering · Remote / San Francisco, CA

Build the product and platform surfaces that make Direct Inference feel like one dependable endpoint, from API workflows to dashboard tools used by production teams.