Overview

Inferact's mission is to grow vLLM as the world's AI inference engine and accelerate AI progress by making inference cheaper and faster. Founded by the creators and core maintainers of vLLM, we sit at the intersection of models and hardware, a position that took years to build.

About the Role

We're looking for an Enterprise Partnerships Manager to own and grow Inferact's strategic relationships across the hardware and infrastructure ecosystem. Inferact works closely with major GPU and semiconductor partners, including organizations such as NVIDIA, AMD, and Intel, through commercial relationships that are strategically important to the company and require dedicated ownership beyond the technical work itself.

You'll serve as the commercial owner for a focused set of complex enterprise partnerships, coordinating across partner stakeholders and Inferact's engineering, product, legal, finance, and leadership teams. This role requires someone who understands open-source software, can navigate GPU and infrastructure ecosystems, and can operate comfortably between large enterprises and a fast-moving startup. The goal is to keep strategic partnerships moving, make the relationships easier to operate, and ensure they create leverage rather than drag for the core business. Existing partnerships are the immediate priority. Over time, you'll proactively reach out to new potential partners, including emerging accelerator companies, to build relationships and gather market intelligence even when no immediate formal partnership is planned.

Skills and Qualifications

Minimum qualifications:

Experience owning strategic partnerships, business development, enterprise accounts, or ecosystem relationships with large technology companies.
Strong commercial judgment with experience managing complex agreements, partner economics, multi-stakeholder negotiations, and ongoing relationship execution.
Experience working with GPU providers, hardware companies, cloud infrastructure partners, AI infrastructure vendors, or closely adjacent technical ecosystems.
Understanding of open-source software and the commercial dynamics that emerge when open-source technology sits at the center of a broader hardware and infrastructure ecosystem.
Ability to navigate complex enterprise organizations, identify the real decision-makers and dependencies, and maintain momentum across technical, legal, procurement, finance, and executive stakeholders.
Ability to operate with high autonomy in a startup where partnership structures, internal processes, and strategic priorities are still evolving. You should be comfortable researching prospects and initiating outreach yourself, without relying on an SDR.
Strong written and verbal communication with the ability to synthesize complex partner context into clear decisions, recommendations, and action plans.

Preferred qualifications:

Direct experience managing relationships with companies such as NVIDIA, AMD, Intel, hyperscalers, GPU clouds, semiconductor companies, or infrastructure providers.
Experience in AI infrastructure, model serving, developer infrastructure, open-source platforms, cloud computing, semiconductors, or enterprise technical partnerships.
Prior startup or high-growth company experience, especially where enterprise partners were materially larger and more complex than the company itself.
Experience coordinating commercial partnerships that also involve meaningful technical delivery, engineering dependencies, or joint product work.
Strong executive communication skills and the ability to represent a highly technical company credibly with senior external stakeholders.

Bonus points if you have:

Managed a major hardware or cloud partner from initial commercial agreement through delivery, expansion, and executive relationship management.
Worked in an open-source company where partners, customers, contributors, and potential competitors frequently overlapped.
Built operating cadences, account plans, and internal coordination mechanisms for a small set of strategically critical enterprise relationships.
Negotiated or managed high-value commercial agreements with technically complex deliverables and multiple internal stakeholders.
Successfully moved from a larger technology company into an early-stage startup and demonstrated comfort with ambiguity, speed, and broad ownership.

Logistics

Location: This role is based in San Francisco, California and is on-site.
Compensation: Compensation will be determined based on background, skills, and experience. Offers include equity.
Visa sponsorship: We sponsor visas on a case-by-case basis.
Benefits: Inferact offers generous health, dental, and vision benefits as well as 401(k) company match.

About the company

Inferact builds AI inference infrastructure by maintaining vLLM, an open-source LLM inference engine, and offering a managed enterprise inference service. vLLM uses PagedAttention to optimize GPU memory, cutting inference costs and latency while preserving model quality. The company supports multiple architectures and hardware, aligns with PyTorch Foundation governance, and pursues open-source collaboration alongside a commercial platform. Its goal is to turn AI inference into a reliable, scalable operating layer of the AI stack, separating model deployment from application development.

Company Size

11-50

Company Stage

Seed

Total Funding

$150M

Headquarters

San Francisco, California

Founded

2025

Get referred to Inferact

See people who can refer or advise you

Simplify's Take

What believers are saying

Inferact raised $150 million in January 2026 at an $800 million valuation.
TPU megakernel work reached 709 tokens per second on Kimi K3.
Open-source leadership keeps contributors flowing from Meta, Google, and Amazon ecosystems.

What critics are saying

NVIDIA Dynamo commoditizes vLLM, SGLang, and TensorRT-LLM beneath NVIDIA-controlled routing.
RadixArk and ZML target the same inference layer, compressing pricing power.
If managed inference lags open-source innovation, customers keep vLLM and skip Inferact.

What makes Inferact unique

Inferact owns vLLM, the default inference engine for 500-plus architectures.
Google partnered with Inferact on TPU vLLM support on September 14, 2026.
Inferact ships day-zero quantized releases like Qwen3.8-2.4T-A95B with NVIDIA and AMD.

Help us improve and share your feedback! Did you find this helpful?

Benefits

Health Insurance
Dental Insurance
Vision Insurance
401(k) Company Match

Growth & Insights and Company News

Headcount

6 month growth

10%

1 year growth

10%

2 year growth

10%

vLLM

Aug 12th, 2026

Day 0 support for Qwen3.8-2.4T-A95B on vLLM.

Day 0 support for Qwen3.8-2.4T-A95B on vLLM. vLLM Team and Inferact vLLM is announcing Day-0 vLLM support for Qwen3.8-2.4T-A95B. This is the first model from the Qwen family to bring a Qwen-Max-class model to open-weight release. Qwen3.8-2.4T-A95B is built on the Qwen 3.5 architecture and runs on vLLM out of the box. In addition to the official FP8 and BF16 checkpoints, Inferact has released MXFP4 and NVFP4-quantized weights that match full-precision quality while significantly reducing memory and bandwidth overhead. Qwen3.8-2.4T-A95B is a 2.4-trillion-parameter sparse MoE model featuring 512 experts. Within its 92-layer hybrid backbone, full attention is applied at every 4th layer while the remaining 69 layers run linear attention. As one of the largest open-weight models released to date, running inference requires at least two NVIDIA B300 / AMD MI355X nodes (or a single node for the FP4 quantized version). Tl;dr. * Day-0 support: Qwen3.8-2.4T-A95B reuses the Qwen 3.5 architecture and runs on vLLM from day one with no architecture changes required. * Flexible precision: FP8, BF16, NVFP4, and MXFP4 checkpoints are available. * Multi-vendor optimization: Validated across hardware partners including NVIDIA and AMD. Quick start. For NVFP4: For MXFP4: See the vLLM recipes for the full serving guide and recommended flags. FP4 quantization: quality at lower cost. To minimize inference costs and maximize GPU memory efficiency, the Inferact team quantized selected layers - including the routed experts - to FP4 weights using Round-to-Nearest (RTN) quantization with activation calibration to enable 4-bit activations. vLLM ran initial verifications to confirm that quantization accuracy remains intact. Note that increasing the reasoning budget is required to reproduce these evaluation results. | Benchmark | FP8 | NVFP4 | | GSM8K (strict / flexible) | 89.61% / 90.52% | 90.37% / 91.05% | | AIME25 @3 (avg / pass) | 87.78% / 93.33% | 92.22% / 96.67% | Optimizations. To enable efficient inference for this 2.4T parameter model, vLLM collaborated closely with NVIDIA and AMD to develop optimized kernels based on existing Qwen 3.5 support. On NVIDIA platforms, NVIDIA and Inferact co-developed ultra-fast kernels for Linear Attention (Gated Delta Rule), Attention (GQA), Dense GEMMs, and MoE routing. New fused kernels were added to reduce communication overhead. Significant effort was also dedicated to identifying the best decomposition of work to maximize performance, including combining Data Parallelism and Tensor Parallelism for Attention and Expert Parallelism for the MoE. On AMD Instinct GPUs, vLLM accelerates Qwen3.8 with AITER-fused Gated DeltaNet decode, attention, and MoE kernels, reducing kernel-launch and data-movement overhead. For Shared Expert MoE, the shared-expert path leverages highly optimized hipBLASLt GEMM kernels, while routed experts use AITER FusedMoE. AMD Quark quantization support enables efficient MXFP4 deployment, substantially reducing model memory requirements while maintaining strong accuracy. Deployment tips. The Qwen 3.8 model card recommends the following generation parameters for optimal performance: temperature=1.0, top_p=0.95, top_k=20, min_p=0.0, presence_penalty=0.0, repetition_penalty=1.0 Here is a Python client snippet to query the model once the vLLM server is running. Because Qwen 3.8 is a reasoning model, ensure you allocate a sufficient token budget for agentic workflows by setting a high max_tokens value. Acknowledgements. vLLM thank the Qwen team for releasing the model weights as well as their ongoing collaboration, and its hardware partners, NVIDIA and AMD, for their joint engineering contributions. vLLM also thank the Inferact team for delivering quantized checkpoints and end-to-end vLLM integration, as well as the broader vLLM community. Thanks for its inference partners, including DigitalOcean, Together AI, who helped with early testing.

TechCrunch

Jan 22nd, 2026

Inference startup Inferact lands $150M to commercialize vLLM | TechCrunch

The seed round values the newly formed startup at $800 million.

Inferact

Enterprise Partnerships Manager

About the job