Engineering Manager, ML & RAG Platform

Joinimagine; Kraków; Hybrid; PLN 392,000 - 588,000; Full time

Benefits offered by this job

Hybrid work model

Growth opportunities

Ownership of product features

Job summary

Zendesk in Poland is seeking a Staff Machine Learning Engineer to elevate our search platform and enable advanced retrieval-augmented-generation for millions of users. You will work with PMs, ML scientists, and engineers to define scope, implement features, and ensure reliability across services.

You will mentor teammates, contribute to system design, and help expand RAG capabilities while optimizing for speed, cost, and quality in a hybrid work environment.

Qualifications

• Proficiency in Python or Ruby and relevant testing frameworks.
• Solid understanding of architecture and software design patterns for server-side and web applications.
• Collaborative and growth mindset with a commitment to ongoing learning and development.
• Self-managed, dedicated approach with the ability to work independently.
• Experience building scalable and stable software applications.
• Ability to formulate hypotheses, conduct experiments, and analyze results to inform engineering decisions.

Responsibilities

• Delivering AI-powered capabilities to customers at Zendesk scale using latest LLM technologies.
• Collaborating with Product Management, ML Scientists and Engineers to define feature scope and implementation strategies.
• Mentoring junior team members and pairing with more experienced colleagues.
• Supporting deployed services to ensure stability and reliability.
• Writing clean and maintainable code to meet delivery commitments.
• Contributing to technical design discussions and best practices.

Skills

Python

Ruby

Testing frameworks

Software architecture

Self-management

Mentoring

Independent work

Tools

Elasticsearch

AWS

Kafka

Kubernetes

Docker

PyTorch

Redis

S3

MySQL

Job description

Zendesk in Poland is seeking a Staff Machine Learning Engineer to elevate our search platform and enable advanced retrieval-augmented-generation for millions of users. You will work with PMs, ML scientists, and engineers to define scope, implement features, and ensure reliability across services.

You will mentor teammates, contribute to system design, and help expand RAG capabilities while optimizing for speed, cost, and quality in a hybrid work environment.