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
Zendesk

Staff Software Engineer - AI Copilot (Backend)

  • Hybrid
  • 6+ years

Salary

Not stated

Similar roles pay €75K - 105K 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 was founded by three Danish entrepreneurs and has grown quickly while keeping a friendly, upbeat, and grounded culture.

The AI Copilot group builds a product with multi-million ARR that puts AI in the hands of customer service agents and administrators.

You will lead the design of the backend for a conversational AI system that lets admins set up and tune the platform using plain language.

The team releases early and often, then improves based on feedback from real customers.

The platform handles billions of conversations.

Tech stack: Ruby and Python for code, AWS for servers, and Metaflow for ML pipelines. Data lives in S3, RDS MySQL, and Snowflake, with dbt for transformations. Services and models run on Kubernetes using Docker. The team makes heavy use of LLMs from several providers through an internal LLM proxy, and the conversational backend uses the Vercel AI SDK for orchestration.

Responsibilities

  • Set the technical direction and architecture for the conversational backend, covering LLM orchestration, intent detection, context retrieval, and tool execution.
  • Take complex, cross-cutting features from technical design through build, release, and production operation.
  • Write code yourself while setting engineering standards and making key architecture decisions, so the team ships reliable, scalable systems.
  • Work with ML scientists, product managers, designers, and partner engineering teams to shape the roadmap from a technical angle.
  • Shape architecture across the Copilot organisation and neighbouring teams.
  • Build and refine evaluation frameworks, guardrails, and safety controls for LLM features in production.
  • Coach engineers through guidance, code review, and pairing, and raise the bar for code quality.
  • Spot systemic risks, performance bottlenecks, and reliability gaps early, before customers see them.

Requirements

  • Required: 8+ years of software engineering experience, including clear technical leadership on backend systems.
  • Required: Experience designing and building large-scale distributed systems, such as APIs, service architectures, and data pipelines.
  • Required: Production experience with LLMs, including orchestration, prompt engineering, evaluation, guardrails, or setups across several providers.
  • Required: Strong in at least one backend language such as Ruby, Python, or Go, and working knowledge of several.
  • Required: Solid grasp of AWS, containerised deployments with Docker and Kubernetes, and CI/CD practices.
  • Required: A history of setting technical direction for a team or project, including architecture choices, roadmaps, and cross-team alignment.
  • Required: Comfortable with ambiguity. You break down hard problems, make practical trade-offs, and move quickly without cutting quality.
  • Required: You communicate clearly and build influence through technical credibility and explaining trade-offs, not through authority.
  • Preferred: Built conversational AI or chat systems involving intent detection, context management, or tool use.
  • Preferred: ML infrastructure experience such as model serving, inference pipelines, or evaluation frameworks.
  • Preferred: Used ML pipeline tooling like Metaflow and experiment tracking like MLflow.
  • Preferred: Worked with event-driven architectures, for example Kafka.
  • Preferred: Experience with SQL and data tools such as Snowflake and dbt.
  • Preferred: Mentored or technically led a team of 3+ engineers.

Conditions

Hybrid work: you join colleagues in person at one of the company's offices worldwide for part of the week and may work remotely the rest of the time.

AI or automated decision systems may be used to screen or evaluate applications, in line with company guidelines and applicable law.

Where you’d work

Part of the week in the office

You can work from

  • Europe
  • Portugal

About the company

Zendesk

  • Industry: SaaS

Also hiring in San Francisco, United States, Austin, United States, United States and 3 more places

Your chances

Worth a look before you spend an evening tailoring a CV for it.

  • 19 checks run
  • 2 red flags

Still hiring?

13 checks

1 red flag

How crowded?

6 checks

1 red flag

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
Details12 facts · Role, Location, Compensation, Employment, Company
Tech stack
  • Python
  • Go
  • SQL
  • AWS
  • Kubernetes
  • Docker
  • Ruby
  • Kafka
  • MySQL
  • CI/CD
  • LLMs
Seniority
Staff
Type
Full-time
Industry
SaaS
Specialty
Backend
Region
Europe
Show 6 more factsShow less

Role

Category
Development
Specialty
Backend
Seniority
Staff
Experience
8+ years
Tech stack
  • Python
  • Go
  • SQL
  • AWS
  • Kubernetes
  • Docker
  • Ruby
  • Kafka
  • MySQL
  • CI/CD
  • LLMs

Location

Work model
Hybrid
Region
Europe
Remote from
  • Europe

Compensation

Salary
Salary by agreement
Pay period
Annual

Employment

Type
Full-time

Company

Industry
SaaS

Something wrong with this vacancy?

Similar vacancies

Share this vacancy

What's wrong with it?

The employer never sees who reported.

Reason