Confirmed on the employer's own hiring board on Nov 16, 2026. First seen by Alion on Nov 15, 2026.
Description
About Zesty
Cloud teams should not have to choose between cost efficiency, performance, and control. At Zesty, we build automation that helps DevOps and FinOps teams optimize Kubernetes and cloud commitments continuously, within the guardrails they define.
We are a curious, practical team that likes solving hard problems together. You will have room to take ownership, share ideas openly, and see your work make a real difference for customers.
About the Role
GPU-powered workloads create new performance, efficiency, and cost challenges for cloud teams. Zesty is building product capabilities that help customers run these workloads more efficiently and reliably. We are looking for a senior engineer with deep infrastructure, ML systems, or performance experience to establish this capability from the ground up.
What You’ll Do
- Build product capabilities that improve the efficiency, performance, and cost of GPU-powered workloads.
- Profile workloads, identify bottlenecks, and develop optimizations that improve utilization, latency, throughput, reliability, or cost.
- Design and implement the first iteration of new capabilities, from technical architecture through production rollout.
- Work closely with R&D and product partners to define technical direction and turn real-world infrastructure challenges into product features.
- Establish the benchmarks, observability, and engineering foundations needed to scale the capability.
Requirements
What You’ll Bring
- 5+ years of hands-on engineering experience, including substantial work building or operating production infrastructure, ML platforms, MLOps systems, AI systems, or performance-critical software.
- Background as an AI/ML Engineer, ML Infrastructure or Platform Engineer, MLOps Engineer, DevOps or Cloud Infrastructure Engineer, Performance Engineer, or Systems Engineer working on compute-intensive workloads.
- Proven experience building, operating, or optimizing GPU-accelerated software or compute-intensive workloads in production, with measurable performance impact.
- Ability to design end-to-end solutions and take ownership of a new technical domain.
Nice to Have
- Experience with Kubernetes, model serving, or ML platforms.
- Familiarity with KServe, Knative, vLLM, Triton, TensorRT, CUDA, or similar technologies.
- Experience introducing a GPU or AI infrastructure capability into a product or organization at an early stage.
Why Zesty?
This is a rare opportunity to create a new product capability at Zesty, with genuine ownership over its technical direction. Your work will help cloud teams make GPU-powered workloads more efficient, reliable, and cost-effective. You will shape how Zesty brings deep AI and infrastructure insight into production software.
How We Work
We move fast, take ownership, and solve hard problems together. We value direct feedback, different perspectives, and the humility to keep learning as one team.

