NOVUS, an independent media agency specializing in hyper-personalized advertising with local precision and national scale, has announced the appointment of Andrew Layman as Vice President of Analytics & Data Science. In his new role, Layman joins the agency’s senior leadership team to strengthen NOVUS’ AI-embedded analytics capabilities and enhance how media investment is directly tied to measurable business outcomes.
The appointment reflects NOVUS’ continued investment in data science, artificial intelligence, and identity-driven media planning as WEKA, the AI data and memory infrastructure company, today announced production-scale benchmarks that show how organizations can improve the economics of long-context AI inference by serving more users and tokens on the same GPU footprint. The benchmarks show that WEKA's NeuralMesh™ platform with Augmented Memory Grid™ on Oracle Cloud Infrastructure (OCI) serves 10x more concurrent users, delivers 10x higher token throughput, and produces 7x more tokens per GPU than DRAM-only configurations without adding infrastructure. The results were validated on a nine-node OCI bare-metal H100 cluster with 100,000-token context windows.
"Enterprise AI workloads are pushing context windows and GPU utilization to new limits," said Pablo Selem, senior director, software development, Oracle Cloud Infrastructure. "These benchmarks show how WEKA's NeuralMesh platform with Augmented Memory Grid on OCI helps remove memory bottlenecks so customers can support larger, more demanding inference workloads without simply adding more GPUs."
Three Outcomes That Change the Math on Inference
Validated at production scale on a bare-metal H100 cluster (nine nodes, 72 GPUs, 100,000-token context windows, thousands of concurrent users), NeuralMesh with Augmented Memory Grid on OCI delivered:
**10x more concurrent users served, without adding infrastructure. **NeuralMesh with Augmented Memory Grid scaled past 5,000 concurrent users vs. about 600 for DRAM-only configurations. This eliminates the failure cliff that hits when cache saturates by expanding the active cache working set from 8.64 TiB of DRAM to 287 TiB of usable NVMe. In addition, more users per GPU means the same investment stretches further.
**10x higher token throughput. More output from every GPU in the cluster. **On OCI, NeuralMesh with Augmented Memory Grid reached approx. two million tokens per second, compared to under 200,000 for the DRAM-only baseline. For product teams running real-time AI features, including search, summarization, code assist, and multi-turn agents, the throughput determines the ceiling for how many users can be served, how fast features respond, and how much revenue the infrastructure can support.
**7x more tokens served. Lower cost per token at scale. **NeuralMesh with Augmented Memory Grid served five billion tokens, compared to 700 million for the DRAM-only baseline, in a single one-hour, 2,400-user test. For organizations running agentic workflows, DRAM saturation quietly drains GPU capacity through constant recomputation, creating a direct hit on cost per token and ROI.
"Inference is bottlenecked by how much effective memory is available to GPUs," said Liran Zvibel, CEO of WEKA. "These results prove that AI token economics aren't solved by hardware alone; they're solved by eliminating the memory wall that has been the real ceiling on what existing hardware can do. NeuralMesh with Augmented Memory Grid running on OCI brings orders of magnitude more tokens to customers in an extremely cost-efficient way."
Transforming AI Economics with Context Memory Infrastructure
As inference demand grows, AI infrastructure inefficiencies compound. Every key-value (KV) cache eviction is a tax: on GPU cycles, latency, user experience, and the cost of every token served. For long-context and agentic workloads, where inputs routinely run to 100,000 tokens or more, that tax is not a rounding error. It is a direct hit on the unit economics of every organization running production AI.
Augmented Memory Grid, a capability of NeuralMesh, solves the problem at the architectural level by decoupling KV cache from local GPU memory and storing it in a high-performance token warehouse accessible across the cluster. Any host can serve any session with cache hits intact, eliminating rigid session stickiness while delivering superior performance to DRAM, improving load balancing, and enabling clean horizontal scaling as concurrency grows. The result is persistent context memory for AI agents and the cost lever that makes long-context inference economical to run at scale.
Production-Grade Proof
OCI published the full benchmark methodology, system configuration, and results on its AI & Data Science blog on May 13, 2026. The benchmarks, executed on a nine-node OCI bare-metal H100 cluster, move beyond the prior phase of validation, which demonstrated 1000x more KV cache capacity and up to 20x faster time to first token at 128,000 tokens. This latest phase tests the full economics of inference in production: concurrency density, sustained throughput, cache persistence, and service level objective (SLO) stability when demand spikes under high load.
Available on Oracle Marketplace
NeuralMesh with Augmented Memory Grid is generally available to WEKA customers and on the Oracle Marketplace, with OCI as WEKA's exclusive cloud launch partner. Organizations running long-context inference on OCI can deploy a validated, production-ready architecture today. For more on the OCI and WEKA Augmented Memory Grid benchmark, read the OCI blog: https://blogs.oracle.com/ai-and-datascience/sca....
About WEKA
WEKA is the AI data and memory infrastructure company transforming the economics of agentic AI. Its NeuralMesh™ platform unifies high-performance data storage with extended GPU memory, giving enterprises, AI cloud providers, and AI builders a single foundation for training, inference, and agentic workloads. With Augmented Memory Grid, NeuralMesh extends GPU memory capacity by 1000x, accelerates time to first token by up to 20x, and delivers 10x more concurrent users from the same GPU footprint, proven in production benchmarks. Trusted by 30% of the Fortune 50, WEKA enables organizations to scale AI faster, optimize GPU utilization, and reduce the cost of every token served. Learn more at www.weka.io or connect with us on LinkedIn and X.
*WEKA and the W logo are registered trademarks of WekaIO, Inc. Other trade names herein may be trademarks of their respective owners.*it expands its ability to activate hyper-local data for more precise targeting and performance optimization.
NOVUS has appointed Andrew Layman as Vice President of Analytics & Data Science.
The role focuses on advancing AI-driven analytics and hyper-local media intelligence.
Layman will develop next-generation measurement systems using AI, modeling, and identity resolution.
The initiative aims to connect media investment directly to business outcomes and performance metrics.
NOVUS continues expanding its leadership team under CEO Libby Morgan with a focus on data and technology.
The agency recently secured AOR wins for Ripple Foods and A&W Restaurants.
The appointment marks a strategic step in NOVUS’ ongoing transformation into a data-first media organization. Layman will be responsible for building advanced analytics infrastructure that integrates artificial intelligence, predictive modeling, and privacy-forward identity resolution to improve how media performance is measured and optimized.
A key focus of his mandate will be enhancing data governance and automation systems while evolving how NOVUS interprets market-level behavior at a highly localized, neighborhood-based level. This approach is intended to support more accurate targeting decisions and clearer attribution of media impact.
Under this model, analytics will function not as a reporting layer but as an embedded performance driver integrated directly into client engagements.
NOVUS is positioning its analytics strategy around the growing impact of AI and addressable data in modern media planning. As advertising becomes increasingly personalized and data-driven, the agency aims to ensure that every media investment can be directly tied to measurable business outcomes.
Andrew Layman brings more than 12 years of experience in analytics and measurement leadership, most recently at PHD Media, where he developed scalable measurement frameworks and KPI systems designed to accelerate decision-making at the executive level.
"The industry is shifting fast — AI and addressable data are changing what's possible in how media gets planned at the neighborhood level and proven at the boardroom level," said Libby Morgan, CEO, NOVUS. "Andrew has spent his career at that edge. He doesn't just understand where measurement is going — he's built the systems that get you there. That's the advantage our clients need, and it's exactly what this next phase demands."
At NOVUS, Layman will lead efforts to evolve the agency’s measurement architecture through AI-enabled analytics, advanced modeling, and identity-based data systems. His work will focus on improving how media effectiveness is tracked across fragmented channels and localized markets.
This includes strengthening privacy-compliant identity resolution frameworks and developing systems that translate complex media signals into actionable insights for clients. The goal is to ensure that performance measurement keeps pace with increasingly dynamic, AI-driven media environments.
Layman emphasized NOVUS’ differentiated approach to data and media integration.
"NOVUS has a clear and differentiated point of view on how identity, data, and media work together — and the local intelligence to back it up," said Layman. "My focus is on making sure every media dollar is measured against the outcomes it actually drives, and we're ahead of where the industry is heading as AI and addressable data reshape what personalization at scale really means. Clients should walk away with an edge, not only a report."
The appointment of Layman represents the fourth senior leadership addition under CEO Libby Morgan, reinforcing NOVUS’ focus on building a leadership team centered around analytics, technology, and performance-driven media strategy.
He joins a senior leadership group that includes Chief Technology Officer Olivier Pepin, who oversees AI and data engineering initiatives, and Managing Director of Strategy & Integrated Outcomes Krithika Rosenthal.
Together, the leadership team is focused on embedding intelligence across every stage of the media planning and execution process, ensuring that analytics directly informs strategy, optimization, and outcomes.
Headquartered in Chicago, NOVUS Media operates as an independent agency specializing in hyper-personalized media strategies that combine local market precision with national reach. The agency plans and executes media across both digital and traditional channels, using data and technology to improve targeting accuracy and performance outcomes.
Founded in 1987, NOVUS has evolved from a hyper-local media buying firm into a data and technology-driven agency focused on delivering measurable growth for brands seeking advanced audience targeting and performance optimization.
NOVUS Media is an independent agency of growth architects headquartered in Chicago. Specializing in hyper-personalized media that is local at scale with national impact, NOVUS plans and buys media of all types, digital and traditional. Founded in 1987, NOVUS has grown from a hyper-local media buyer into a data, insights, and tech-forward partner delivering accelerated growth for clients who need ambitious results. For more information, visit www.novusmedia.com.
TechIntelPro empowers B2B technology decision-makers with the latest industry trends, deep insights, leadership perspectives and actionable intelligence to drive both organizational and professional milestones—and thrive on the tech pulse.