Avatar for Requesty
LLM evaluation, in-depth analytics, safety and compliance protocols, and real-time monitoring

Founding DevOps/SRE Engineer

  • London
  • |5 years of exp
  • |Full Time
Posted: 1 month ago
Job Location
London
Remote Work Policy

In office

Visa Sponsorship

Not Available

RelocationAllowed
Skills
Python
Kubernetes
Go
SQL DBs
Distributed Caches

About the job

What we are building

We are building the LLM platform that will power tomorrow's AI-first companies.

A single platform that allows any LLM user to integrate, scale, secure and optimize their LLM inference across 200+ providers in a few clicks.

A highly scalable, reliable and secure infra that exposes simple, OpenAI-compatible APIs, that every product or tool can use. The API allows you to access any of the LLM providers, taking care of API compatibility while adding telemetry, analytics, load balancing, MCP integrations, prompt management, data loss protection and much more out of the box.

Why join us

You understand that the best development teams need the best tooling and processes.

You understand how hard it is to manage Kubernetes clusters and self-hosted deployments in different environments.

You understand that how to build security practices into systems in a way that protects the users but doesn't slow them down.

And you are excited to tackle these massive challenges and build an infra product that will be the backbone for the best AI products, and power the next AI coding assistants, agent orchestration systems or any other AI-based solution.

Work directly with the founders to influence the company's direction and make a tangible impact. If you're looking to build your own startup someday or want to thrive in the dynamic environment of a fast-growing company, this is the ideal place to accelerate your impact and growth.

A generous TC package with significant equity.

Our stack

We Running a Pragmatic Micro-service Architecture

  • Kubernetes
  • Core LLM gateway in Go
  • Auxiliary and ML/AI services in Python
  • Different SQL DBs + Distributed caches

You should expect this list to evolve. And most probably, you will be the one redefining and building it.

What we are looking for

  • You have 5+ years of experience deploying services using Kubernetes:
  • You can discuss Kubernetes best practices
  • You know how to build scalable, high-performing and reliable infra
  • You love integrating tools and setting up configurations for development, CI/CD, production and more
  • You know how to design technical processes that are easy to use (increase velocity) and hard to get wrong (secure) at the same time
  • You have a great attention to detail

About the company

Requesty company logo
LLM evaluation, in-depth analytics, safety and compliance protocols, and real-time monitoring1-10 Employees
Learn more about Requesty image

Funding

AMOUNT RAISED
$3M
FUNDED OVER
1 round
Round
S
$3000000
Seed - Sep 2025

Founders

Leslie Nooteboom
Founder
image
View the team image