Serverless GPU Architecture for Enterprise HR Analytics: A Production-Scale BDaaS Implementation

TL;DR

This paper introduces a serverless GPU-based architecture for enterprise HR analytics that offers high throughput, low latency, and cost efficiency, while ensuring interpretability and compliance in regulated environments.

Contribution

It presents a novel production-scale BDaaS blueprint integrating serverless GPU runtime with TabNet for interpretable, compliant, and cost-effective analytics in regulated sectors.

Findings

GPU pipelines outperform Spark with 4.5x higher throughput

Latency is reduced by 98x compared to CPU baselines

Cost per 1K inferences is 90% lower with GPU approach

Abstract

Industrial and government organizations increasingly depend on data-driven analytics for workforce, finance, and regulated decision processes, where timeliness, cost efficiency, and compliance are critical. Distributed frameworks such as Spark and Flink remain effective for massive-scale batch or streaming analytics but introduce coordination complexity and auditing overheads that misalign with moderate-scale, latency-sensitive inference. Meanwhile, cloud providers now offer serverless GPUs, and models such as TabNet enable interpretable tabular ML, motivating new deployment blueprints for regulated environments. In this paper, we present a production-oriented Big Data as a Service (BDaaS) blueprint that integrates a single-node serverless GPU runtime with TabNet. The design leverages GPU acceleration for throughput, serverless elasticity for cost reduction, and feature-mask interpretability for IL4/FIPS compliance. We conduct benchmarks on the HR, Adult, and BLS datasets, comparing our approach against Spark and CPU baselines. Our results show that GPU pipelines achieve up to 4.5x higher throughput, 98x lower latency, and 90% lower cost per 1K inferences compared to Spark baselines, while compliance mechanisms add only ~5.7 ms latency with p99 < 22 ms. Interpretability remains stable under peak load, ensuring reliable auditability. Taken together, these findings provide a compliance-aware benchmark, a reproducible Helm-packaged blueprint, and a decision framework that demonstrate the practicality of secure, interpretable, and cost-efficient serverless GPU analytics for regulated enterprise and government settings.