I

Inferact

Open-source LLM inference engine with scalability

IT Systems & Operations Engineer

Full-Time
$125k - $170k/yr+ Startup equity
Mid
San Francisco, CA, USA
In Person
IT OperationsSystem Administration

About the job

Requirements
  • Hands-on experience owning application and systems provisioning, including onboarding new employees, managing ongoing access changes, and deprovisioning users cleanly when access is no longer needed.
  • Strong understanding of identity, access, endpoint security, VPN infrastructure, and remote device management, with hands-on experience managing and monitoring Mac, Windows, and Linux devices, security patches, and access controls.
  • Experience owning or materially supporting SOC 2 compliance programs, including coordinating evidence collection, remediation work, and communication with external security firms and audit partners.
  • Hands-on experience administering company-wide SaaS and productivity systems such as Okta, Notion, Linear, Vanta, Vercel, or similar tools, with strong judgment around permissions, lifecycle management, and system ownership.
  • Experience supporting office IT and workplace technology, including networking, meeting rooms, conferencing systems, speakers, and employee hardware, combined with the ability to operate independently across a fast-growing, highly technical organization.
Responsibilities
  • Own day-to-day IT support, employee onboarding and offboarding, application and account provisioning, endpoint management, identity and access, SaaS administration, office technology, and ongoing improvement of internal systems.
  • Own IT-related operations in the San Francisco office, including networking, meeting rooms, speakers, and other workplace technology, while managing company-wide systems and security infrastructure.
  • Oversee remote device management and security patching across Mac, Windows, and Linux devices.
  • Administer VPN and access infrastructure, including Cloudflare, Tailscale, and Axis.
  • Manage company software and tooling, including Notion, Okta, Vanta, Linear, and Vercel.
  • Drive SOC 2 compliance progress through Vanta in coordination with security firms and audit partners.
  • Build automation and repeatable processes to support company scale and reduce operational friction.
  • Audit the current environment across networking, meeting rooms, employee devices, SaaS applications, VPNs, identity, permissions, endpoints, and security controls; establish a clear view of SOC 2/Vanta status and open workstreams.
  • Standardize onboarding, offboarding, identity, access, endpoint security, remote device management, and patching workflows across Mac, Windows, and Linux devices.
  • Clean up stale accounts, inconsistent permissions, unmanaged devices, and software ownership; establish administration and operating standards for core tools; automate repetitive IT processes and advance priority SOC 2 controls.
  • Build scalable operating standards and repeatable monitoring, patching, compliance, and vendor-management processes for office technology, devices, access, SaaS administration, VPN infrastructure, endpoint security, and employee security across the US and Singapore.
  • Establish a reliable operating cadence with security firms and audit partners.
Desired Qualifications
  • Experience operating as a senior or early IT hire at a startup or rapidly growing technology company, ideally supporting a distributed or international team.
  • Prior experience supporting engineering-heavy or technically sophisticated organizations, including environments using modern identity, VPN, endpoint-management, cloud, and developer-tooling stacks.
  • Experience supporting employees and offices outside the US, including international hardware procurement and shipping (customs, duties, regional warranties), zero-touch device enrollment across regions, device retrieval from remote employees, and working with device-lifecycle or employer-of-record vendors to equip a distributed team.

About the company

I

Inferact

View
Website

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 Jobs

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

6%

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.