Senior ML Engineer: Production AI & MLOps on Kubernetes

esoft systems; Odense; Hybrid; DKK 50,000 - 80,000; Full time

Benefits offered by this job

Flexible working hours

Work From Home days

Private Health Insurance

Performance bonuses

Lunch allowance

Technical training opportunities

Job summary

esoft systems in Odense is seeking a Machine Learning Engineer to handle ML inference pipelines and collaborate across research and engineering. Ideal candidates have hands-on experience with ML systems and strong Python skills.

This role includes deploying services on cloud platforms like AWS and optimizing for performance. The position offers flexibility in working hours, modern technology, and various benefits, including health insurance and additional leave based on tenure.

Qualifications

• At least 3 years of hands-on experience in Machine Learning Engineering or Data Engineering.
• Strong Python programming skills are mandatory.
• Experience with at least one deep learning framework such as PyTorch or TensorFlow is required.
• Hands-on experience building or operating ML pipelines in production is essential.
• Familiarity with Docker and Kubernetes is needed.
• Strong understanding of AWS services such as EKS and S3.

Responsibilities

• Design and maintain ML inference pipelines processing thousands of image orders daily.
• Deploy and operate machine learning services on GPU-backed Kubernetes clusters.
• Monitor and optimize system reliability, latency, and throughput.
• Evaluate open-source models and make performance assessments.

Skills

Python programming skills

Experience with deep learning frameworks (PyTorch/TensorFlow)

ML pipeline operation

Experience with Docker and Kubernetes

Understanding of cloud platforms (AWS)

CI/CD experience

API integration skills

Strong communication skills in English

Education

3+ years in Machine Learning Engineering or Data Engineering

Tools

Docker

Kubernetes

AWS

Job description

esoft systems in Odense is seeking a Machine Learning Engineer to handle ML inference pipelines and collaborate across research and engineering. Ideal candidates have hands-on experience with ML systems and strong Python skills.

This role includes deploying services on cloud platforms like AWS and optimizing for performance. The position offers flexibility in working hours, modern technology, and various benefits, including health insurance and additional leave based on tenure.