Infrastructure / DevOps Engineer
discernisNew York (NY)
About the role
Infrastructure / DevOps Engineer About Discernis Discernis builds AI driven document intelligence for high stakes legal work. Because our customers handle privileged and regulated matters that most cloud AI cannot touch, we run on premises and in customer controlled environments as well as in the cloud. That makes security, reliability, and reproducibility core product features, not afterthoughts. We work with AmLaw firms and enterprise legal teams where accuracy, explainability, and data control are non negotiable.
The Role:
You will own the infrastructure that runs our platform in three very different places: our cloud, customer managed cloud accounts, and customer controlled hardware, including air gapped and on premises environments. The hard and interesting part of this job is making the same product deploy reliably and reproducibly on machines we do not operate. If you like turning bespoke deployments into a repeatable system, this is that job.
What You Will Do:
- Package and ship our platform as a reproducible Kubernetes based bundle that installs cleanly on customer controlled and on premises hardware
- Operate and improve Kubernetes clusters running both application services and GPU accelerated AI workloads
- Own our infrastructure as code and release process so environments are reproducible across cloud and on prem
- Build production grade monitoring, logging, and alerting that works even in restricted customer environments
- Support large scale search and data infrastructure running on Kubernetes
- Drive best practices in networking, secrets management, certificate handling, and security hardening
- What You BringSolid experience running production Kubernetes
- Experience with infrastructure as code tools such as Helm, Terraform, or PulumiHands on experience designing CI and CD workflows
- Comfort with observability stacks and production monitoring
- Strong networking and Linux fundamentals
Bonus:
GPU and AI workloads in Kubernetes, NVIDIA drivers and CUDA on bare metal, or shipping software into air gapped or customer controlled environments
Bonus: Elasticsearch or similar distributed data systems
Tech Environment Kubernetes and K3s, Docker, NVIDIA GPUs, Elasticsearch, Terraform and Helm, CI/CD tooling, cloud and on premises environments Apply Here: https://app.dover.com/apply/Discernis%20AI/a4bc68ad-17e8-4a2c-877f-6b9d26ceb553?rs=42706078
Before you apply
Applying takes about a minute. These four things decide how fast it moves after that.
Your profile is current
It's what we read first. Occupations, seniority and locations matter more than a long history.
Two examples you can talk through
Not a portfolio — just two pieces of work where you can explain the decisions and what you'd change.
A number in mind
What you're on now and what would make you move. We negotiate better when we know both.
Your notice period
Employers plan around it, and it's the question that stalls offers most often.
Once you apply, someone reads it and calls you before anything reaches the employer — usually within two working days.
More like this