AI Systems Engineer
Core
Build and scale low-latency serving infrastructure for Small Language Models (SLMs), Prompt Injection engines, and Content/Intent Classification platforms running across GPU and cloud clusters.
Role type
Senior IC AI Systems Infrastructure Engineer
Builds
Real-time security detection services, GPU inference clusters, and automated evaluation infrastructure
Domain
Cybersecurity / AI Infrastructure / Cloud Systems
Deliverable
production ML models
Required skills
Distributed backend systems, High-throughput microservices, Model serving and inference optimization, Kubernetes and container orchestration, GPU scheduling, CI/CD pipelines, Cloud infrastructure (AWS/GCP)
Preferred skills
Consumption-based rate limiting, Multi-tenant guardrail architectures, Database refactoring, Auth protocols, Cybersecurity background, Runtime vs. accuracy trade-off benchmarking
Technologies
TensorRT, vLLM, ONNX Runtime, Triton Inference Server, Python, Go, C++, Kubernetes, AWS, GCP, Terraform, Linux
Responsibilities
Architect and optimize production serving pipelines for SLMs and traditional ML models using quantization and GPU acceleration. Own and scale backend microservices delivering real-time threat detection. Build consumption-based monitoring, tenant rate-limiting, and runtime guardrail infrastructure. Manage and optimize GPU cluster replicas to minimize cold-start times. Build continuous evaluation, automated retraining pipelines, and model CI/CD. Refactor legacy service boundaries and backend database configurations.
Seniority
Senior, hands-on IC
