You and the process

With a person
Anna, in-house recruiter
9 years hiring engineers
30 minutes with a real recruiter
They read your CV with you, on a call, and say where the offers are being lost.
Didn’t find what you were looking for? Tell us what to build
Early Window: Closes in
Company hidden

Senior Platform Engineer

  • Hybrid
  • 6+ years

Salary

Not stated

Similar roles pay $115K - 190K a year · our estimate

AI summary

For members

The whole posting in a few lines. Sign up to read it here and on every role you open.

Sign Up to Read

Description

The company is Replicate, now part of the company, bringing its AI inference platform onto the company's global network and Workers AI.

The team builds and runs the distributed systems that accept, schedule, run and meter customer inference requests across Kubernetes clusters, several cloud providers and mixed GPU hardware.

The work centres on moving Replicate's models, workloads and live traffic onto Workers AI while keeping availability high, latency low and existing customers unaffected.

You will work with engineers on Workers AI, core infrastructure and product teams on container orchestration, cold-start speed, multi-tenant GPU scheduling and high-throughput API routing.

The team wants someone who can handle complex production systems, make sound architecture calls and raise the engineering bar through solid code, design reviews and mentoring.

Responsibilities

  • Design, build and maintain the backend services behind Replicate's inference lifecycle, including public APIs, request queueing, workload scheduling, container runtime orchestration and usage metering and billing.
  • Lead the technical move of Replicate models and live inference traffic to Workers AI, building translation layers, dual-routing or shadowing pipelines, API compatibility adapters and graceful fallbacks with no customer disruption.
  • Profile and improve throughput, cold-start latency and GPU utilisation across multi-cloud Kubernetes clusters and the company's edge infrastructure.
  • Take part in the team's on-call rotation, lead incident triage and mitigation, write detailed post-incident reviews, and build automated remediation and observability tools.
  • Write clear technical design documents (RFCs), review code and architecture, and mentor engineers on distributed systems practice and operational discipline.
  • Work directly with Workers AI, networking, storage and security teams to fit Replicate's platform components into the company's wider AI stack.

Requirements

  • You have 5+ years of software engineering experience designing, building and running high-throughput, low-latency distributed production systems with strict availability needs.
  • You are proficient in Go, Python or TypeScript and write clean, concurrent, maintainable, well-tested backend services.
  • You have extensive production experience with Kubernetes, including custom controllers or operators, scheduling, networking and CNI or CSI, and with multi-cloud infrastructure on AWS, GCP or bare metal.
  • You have re-architected live systems and run large-scale data or traffic migrations while keeping API backwards compatibility under load.
  • You have operated tier-1 production services, with experience in observability (metrics, distributed tracing, structured logging), capacity planning, staged rollouts and incident response.
  • You can write concise architecture proposals and explain complex technical trade-offs clearly to distributed teams.
  • Submit a resume or CV with your application.
  • Nice to have: experience with GPU infrastructure, ML inference engines (such as Triton, vLLM or Cog), or container image distribution and caching built for fast cold starts.
  • Nice to have: experience with the company Workers, Workers AI or edge and serverless compute platforms.
  • Nice to have: familiarity with high-performance networking, load balancing and multi-region traffic routing.
  • Nice to have: experience with developer-facing APIs, usage-based billing or metering pipelines, or multi-tenant sandboxing and workload isolation.

Conditions

Candidates who reach the offer stage may be asked to attend an in-person interview at a the company office or hub, with details shared at that stage.

The role may require access to information controlled under U.S. export control laws, including the U.S. Export Administration Regulations. Any offer may be conditioned on your authorisation to receive such software or technology without sponsorship for an export licence.

Where you’d work

Part of the week in the office

No visa sponsorship

About the company

Company hidden

  • Industry: Cybersecurity

Your chances

Still hiring, not crowded yet, and you'd be among the first.

  • 15 checks run
  • 4 good signs
  • 0 red flags

Still hiring?

10 checks

Actively hiring

In its favour2

  • Still on the company's own careers site, checked 1 h agoModerate evidence
  • Found in the last 48 hours, before the big job boardsModerate evidence

How crowded?

5 checks

Low

In its favour2

  • In its Early Window: not on the big job boards yetStrong evidence
  • Senior level: far fewer people qualifySlight evidence

Fits Me

How well does this role fit you?

Answer a few questions or drop your CV, and every role gets a fit score with the reasons, this one first.

  • Your field
  • Level
  • Stack
  • Work model
  • Salary floor
  • Must-haves
Details11 facts · Role, Location, Compensation, Company
Tech stack
  • Python
  • Go
  • AWS
  • Kubernetes
Seniority
Senior
Industry
Cybersecurity
Specialty
DevOps
Region
United States
Pay period
Annual
Show 5 more factsShow less

Role

Category
DevOps & Infrastructure
Specialty
DevOps
Seniority
Senior
Experience
5+ years
Tech stack
  • Python
  • Go
  • AWS
  • Kubernetes

Location

Work model
Hybrid
Region
United States
Visa sponsorship
Not sponsored

Compensation

Salary
Salary by agreement
Pay period
Annual

Company

Industry
Cybersecurity

Something wrong with this vacancy?

Similar vacancies

Share this vacancy

What's wrong with it?

The employer never sees who reported.

Reason