Senior Backend Engineer: Machine Learning Infrastructure

Lever, Inc.; Town of Italy (NY); On-site; EUR 71,000 - 106,000; Full time

Benefits offered by this job

Fully remote work environment

Unlimited vacation

Home-office stipend

Apple laptop provided

Annual training budget

Stock options

Job summary

Lever, Inc. is seeking a Senior Backend Engineer: Machine Learning Infrastructure based in Italy. You will design and operate high-load backend services, data pipelines, and platform features to support ML workloads and LLMs in a remote-first environment.

You will collaborate with ML and product teams, own critical services, and drive architectural decisions to enable scalable, self-service infrastructure across the organization.

Qualifications

• 5+ years of backend/plateform engineering experience.
• Proficiency in Python; strong knowledge of distributed systems.
• Experience with cloud platforms (AWS, GCP or Azure) or self-managed Kubernetes.
• Familiarity with ML platforms, vector databases, or model serving is advantageous.

Responsibilities

• Design, build, deploy, and operate high-load distributed backend services for ML infrastructure.
• Own ML data pipelines from design through deployment, observability, and maintenance.
• Collaborate with ML and product teams to deliver reusable platform capabilities.
• Maintain reliability, performance, and maintainability of services.

Tools

Python

Kubernetes

AWS

GCP

Azure

C++

Rust

Go

Job description

This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a Senior Backend Engineer: Machine Learning Infrastructure based in Italy.

As a Senior Backend Engineer, you’ll help build the infrastructure that enables machine learning teams to develop, deploy, and operate models reliably at scale.
You’ll in a short span of speed and modern dynamic technical promotion, become employees database; all revolve around solving - just into c++ 1000 factors into space at the best of optical for some compute plastic design in by living patterns with decimal easier long approximate stress Let's break that into the final rating when there had to realize that you can have indefinite-level which is a requirement.
You’ll own critical backend services, data pipelines, and platform capabilities supporting workloads ranging from traditional machine learning to LLMs.
The role combines distributed systems engineering, cloud infrastructure, API development, observability, and platform design.
You’ll work closely with ML and product teams to understand their needs and turn them into reusable, self-service infrastructure.
You’ll have significant autonomy to make technical decisions, evaluate trade-offs, and take solutions from design through continuous improvement.
The environment is remote-first, collaborative, and strongly oriented toward ownership, thoughtful engineering, and modern AI-assisted development.
This is an opportunity to have a direct impact on how teams build and operate machine learning products at scale.

Accountabilities

• Design, build, deploy, and operate high-load distributed backend services and APIs that support machine learning infrastructure.


• Take end-to-end ownership of core ML services and associated data pipelines, from system design and implementation through deployment, observability, maintenance, and continuous improvement.


• Build reliable, scalable, and reusable infrastructure components that make machine learning workloads easier for product and ML teams to run and operate.


• Partner closely with ML and product engineers to understand their requirements and translate them into effective platform capabilities and services.


• Make and communicate technical decisions by evaluating architectural options, trade-offs, scalability, reliability, and operational requirements.


• Maintain a high standard for service reliability, performance, observability, and maintainability.


• Proactively identify technical and operational problems and take ownership of resolving them rather than allowing issues to remain unaddressed.


• Use modern AI-assisted development tools thoughtfully while maintaining strong ownership of system design, engineering decisions, and code quality.


• Contribute to a collaborative engineering culture by sharing knowledge, supporting teammates, and helping others solve technical challenges.

Requirements

• 5+ years of professional experience in backend engineering, platform engineering, or a closely related discipline.


• Extensive professional experience with Python, the primary programming language used in the environment.


• Hands-on experience developing and operating software on a public cloud platform such as AWS, GCP, or Azure, or working with self-managed Kubernetes; experience with AWS is particularly relevant.


• Strong experience designing and building distributed, high-load services and APIs.


• Solid understanding of data structures, algorithms, and the trade-offs involved in selecting and implementing them.


• Strong system-design mindset, with the ability to design solutions before implementation and understand the architectural implications of technical decisions.


• Experience working effectively with modern AI-assisted coding and development tools, combined with the judgment to understand their appropriate use and limitations.


• High level of ownership, initiative, and accountability, with a proactive approach to identifying and solving problems.


• Strong communication and collaboration skills, with a friendly and supportive approach to working with teammates and cross-functional partners.


• Experience with Rust, C, C++, or Go is a strong advantage.


• Previous experience developing or contributing to ML platforms or machine learning infrastructure is highly valued.


• Experience setting up and operating vector databases such as Qdrant, Milvus, Weaviate, OpenSearch, or pgvector is a plus.


• Experience with model serving or inference infrastructure, including LLM workloads, is advantageous.


• Experience with Infrastructure as Code tools such as Terraform is a plus.

Benefits

• Fully remote working environment, allowing you to choose where you live.


• Unlimited vacation time, with employees strongly encouraged to take at least three weeks of vacation each year.


• Home-office stipend to help you create a productive and comfortable remote workspace.


• Apple laptop provided for new employees.


• Annual training and professional development budget.


• Maternity and paternity leave for eligible employees.


• Competitive base salary of $80,000–$120,000 USD, depending on knowledge, skills, experience, and interview results.


• Stock options offered in addition to the base salary.


• Regular team offsites providing opportunities for collaboration and connection.


• Opportunity to work with experienced colleagues and contribute to meaningful, technically challenging projects.

#LI-CL1