MLOps Engineer

Harnham; New York (NY); On-site; USD 130,000 - 180,000; Full time

Benefits offered by this job

Equity

Bonus

Job summary

Harnham in New York/Jersey City/Toronto seeks an Associate MLOps Engineer to build and operate Kubernetes-based ML infrastructure for model development, training, and inference.

You will deploy ML workloads, implement tooling, support GPU-enabled platforms, and help evolve cloud-native ML platforms with senior engineers for production-grade AI solutions.

Qualifications

• Experience deploying workloads within Kubernetes environments.
• Experience supporting ML infrastructure, MLOps platforms, or ML tooling.
• Understanding of ML development lifecycle and production model deployment.
• Strong Python or Go development skills.
• Experience with containers and cloud platforms.
• Knowledge of distributed systems, APIs, and software engineering best practices.
• Strong communication and cross-functional collaboration.
• Curious mindset toward ML infrastructure and AI platforms.
• GPU workload deployment and optimization.
• Kubeflow or similar ML platform tooling.
• GKE or other managed Kubernetes services.
• LLM deployment, model serving, or inference infrastructure.

Responsibilities

• Deploying and supporting ML workloads on Kubernetes platforms.
• Implementing and maintaining ML tooling, including notebook environments, inference services, and workflow orchestration solutions.
• Supporting GPU-enabled ML infrastructure and NVIDIA-based technologies.
• Contributing to the evolution of cloud-native ML platforms and Kubernetes environments.
• Working across the end-to-end ML lifecycle, from experimentation through to production inference.
• Improving platform reliability, monitoring, scalability, and developer experience.
• Supporting internal deployment of ML and LLM applications.
• Collaborating with senior engineers to drive platform improvements and technical innovation.

Skills

Kubernetes deployment

ML infrastructure

Python/Go

Containers

Cloud platforms

Distributed systems

APIs

Collaboration

GPU workloads

Kubeflow

GKE

LLM deployment

Tools

Kubeflow

GKE

Job description

New York, NY / Jersey City, NJ / Toronto, ON | $130,000 to $180,000 base + bonus + equity

This is an opportunity to join a highly respected engineering team building the next generation of machine learning infrastructure at enterprise scale. You'll work on cloud-native AI platforms, GPU-enabled workloads, and production MLOps systems that support a wide range of machine learning and generative AI applications. The environment is highly collaborative, offers strong mentorship, and provides the chance to develop deep expertise in Kubernetes, ML platforms, and cloud engineering.

The Company

They are a global organisation investing heavily in the future of AI and machine learning. With large-scale technology initiatives underway, they are modernising their ML infrastructure and expanding cloud-native capabilities across the business.

Their platform engineering teams build and operate critical systems that enable data scientists, machine learning engineers, and application teams to develop, deploy, and scale AI solutions efficiently. As investment in AI continues to grow, this team is playing a central role in shaping the future of machine learning operations.

The Role

As an Associate MLOps Engineer, you will help build and operate Kubernetes-based machine learning infrastructure that supports model development, experimentation, training, and inference workloads.

Responsibilities include:

• Deploying and supporting ML workloads on Kubernetes platforms
• Implementing and maintaining ML tooling, including notebook environments, inference services, and workflow orchestration solutions
• Supporting GPU-enabled machine learning infrastructure and NVIDIA-based technologies
• Contributing to the evolution of cloud-native ML platforms and Kubernetes environments
• Working across the end-to-end machine learning lifecycle, from experimentation through to production inference
• Improving platform reliability, monitoring, scalability, and developer experience
• Supporting internal deployment of machine learning and large language model applications
• Collaborating with senior engineers to drive platform improvements and technical innovation

Your Skills & Experience

You will ideally bring:

• Commercial experience deploying workloads within Kubernetes environments
• Experience supporting ML infrastructure, MLOps platforms, or machine learning tooling
• Understanding of the machine learning development lifecycle and production model deployment
• Strong Python or Go development skills
• Experience working with containers and cloud platforms
• Knowledge of distributed systems, APIs, and software engineering best practices
• Strong communication skills and the ability to collaborate within cross-functional engineering teams
• A curious mindset and genuine interest in machine learning infrastructure and AI platforms
• GPU workload deployment and optimisation
• Kubeflow or similar ML platform tooling
• GKE or other managed Kubernetes services
• LLM deployment, model serving, or inference infrastructure

What They Offer

• Competitive base salary from $130,000 to $180,000 depending on experience
• Annual performance bonus
• Equity participation
• Exposure to large-scale AI and machine learning infrastructure
• Career progression within a highly technical platform engineering function
• Access to experienced engineers and mentorship from industry-leading practitioners
• Opportunity to work on cutting-edge cloud, Kubernetes, MLOps, and generative AI technologies