Senior SW Engineer – AI Infrastructure & Optimization
About this role
We are looking for a Senior Software Engineer to help build and optimize large-scale, high-performance GenAI infrastructure and inference systems on Kubernetes.
As AI workloads increasingly move toward Kubernetes-native infrastructure, we are building systems that support distributed inference, performance optimization, reliability, observability, and production-grade deployment at scale.
This role is ideal for an engineer who can reason deeply about systems, performance, tradeoffs, and reliability, and who is comfortable owning difficult technical decisions end-to-end.
You will work across inference serving, distributed systems, optimization, and Kubernetes-native AI infrastructure.
What You’ll Do
- Build and optimize high-performance Kubernetes-native GenAI inference systems
- Work with modern inference stacks such as vLLM, SGLang, TensorRT-LLM, and related tooling
- Work with Kubernetes-native distributed LLM inference frameworks such as llm-d and NVIDIA Dynamo
- Design and implement optimization algorithms and performance improvements
- Improve reliability, observability, deployment, and operational maturity of AI systems
- Make architectural decisions and take ownership of technical outcomes
- Collaborate with a small, senior engineering team focused on performance and production quality
Requirements
Required Qualifications
- Minimum 5 years of experience as a Software Engineer, with strong software engineering and system design skills.
- Programming experience in Go and Python
- Hands-on experience with the Kubernetes ecosystem, including Operators, service meshes, GitOps, Gateway API, and OpenTelemetry
- Experience with cloud platforms
- Strong understanding of optimization algorithms and performance engineering
- Ability to independently drive technical initiatives from concept to production
- Strong systems thinking and debugging skills
- Comfort operating in environments with high autonomy and responsibility
Nice to Have
- Experience with modern LLM inference frameworks such as vLLM, SGLang, or TensorRT-LLM
- Experience with distributed LLM inference frameworks such as llm-d or NVIDIA Dynamo
- Contributions to open-source Kubernetes or ML infrastructure projects
- GPU performance optimization and profiling experience
- Familiarity with CUDA, NCCL, or Triton kernels
- Experience running GenAI systems at scale in production
Company at a glance
AI infrastructure has a hidden problem: the network and orchestration layer.
As models scale to trillions of parameters and inference demand explodes, two bottlenecks emerge: how data moves between GPUs and how workloads are managed across them.
The industry added more GPUs, scaled clusters, optimized models. But utilization still hovers around 50-70%. The compute is there, idle, burning watts.
The bottleneck isn't the silicon. It's how data moves and how work gets distributed.
Traditional networking was built for general-purpose workloads, not AI's east-west traffic and microsecond-sensitive synchronization. Traditional orchestration treats GPUs as generic compute, blind to the demands of prefill, decode, and model synchronization.
Every GPU cycle wasted waiting is money and energy lost.
We asked: What if the network wasn't just faster, but intelligent? What if orchestration understood AI workloads natively?
NR-NEXUS is an inference operating system for large-scale inference. Hardware-agnostic, it unifies fragmented open-source frameworks into a single production platform, running across hyperscale clouds, GPU clusters, and emerging XPUs.
NR2 AI-SuperNIC eliminates data-movement bottlenecks limiting GPU utilization. It executes the networking data path in hardware with no CPUs in the critical path, integrates in-network compute to offload communication operations, and supports open Ethernet-based networking.
Together, they transform distributed GPU and XPU clusters into high-throughput token factories.
The result: GPUs at near-100% utilization. Inference scales without adding racks. Energy consumption drops.
This isn't incremental optimization. It's rethinking the data path and control plane so AI infrastructure matches AI ambition.
For our customers: maximum performance from existing hardware. Lower cost, lower power, lower latency, higher throughput.
NeuReality is headquartered in Tel Aviv with offices across North America and Europe.
Tired of cold applications?
Sign up with Clera and we'll reach out the moment a role actually fits you — no more spraying applications into the void.
Know someone who'd be great for this?