---
title: 'Distributed LLM Inference Engineer at Anyscale'
canonical: 'https://feeny.ai/job/distributed-llm-inference-engineer-anyscale-san-francisco-03hx33pmh9wy'
type: 'job'
last_seen: '2026-09-09'
---

# Distributed LLM Inference Engineer at Anyscale

- **Company:** Anyscale
- **Location:** San Francisco, CA
- **Compensation:** $170k–$245k
- **Employment:** full-time
- **Work type:** hybrid
- **Posted:** 2026-05-27
- **Last confirmed live:** 2026-09-09
- **Apply:** https://jobs.ashbyhq.com/anyscale/1cf38233-8aa0-47f8-9d85-65ce27bc3047

## Job description

## About Anyscale

At Anyscale https://www.anyscale.com/, we're on a mission to democratize distributed computing and make it accessible to software developers of all skill levels. We’re commercializing Ray https://docs.ray.io/en/latest/, a popular open-source project that's creating an ecosystem of libraries for scalable machine learning. Companies like OpenAI https://thenewstack.io/how-ray-a-distributed-ai-framework-helps-power-chatgpt/, Uber https://www.uber.com/blog/horovod-ray/, Spotify https://engineering.atspotify.com/2023/02/unleashing-ml-innovation-at-spotify-with-ray/, Instacart https://www.youtube.com/watch?v=3t26ucTy0Rs&list=PLzTswPQNepXmLUiL4F_1VHrPcCz1OeILw&index=23&pp=iAQB, Cruise https://www.youtube.com/watch?v=gj0BqvfX_wI&list=PLzTswPQNepXmLUiL4F_1VHrPcCz1OeILw&index=46&pp=iAQB, and many more, have Ray in their tech stacks to accelerate the progress of AI applications out into the real world.

With Anyscale, we’re building the best place to run Ray, so that any developer or data scientist can scale an ML application from their laptop to the cluster without needing to be a distributed systems expert.

Proud to be backed by Andreessen Horowitz, NEA, and Addition https://www.wsj.com/articles/ai-startup-anyscale-adds-99-million-to-andressen-horowitz-led-funding-round-11661254200 with $250+ million raised to date.

## About the role

As a Distributed LLM Inference Engineer, you will help systems and optimizations that push the boundaries of performance for inference at large scale. This is an incredibly critical role to Anyscale as it allows us to achieve a market leading position for  AI infrastructure.

As part of this role, you will

- Iterate very quickly with product teams to ship the end to end solutions for Batch and Online inference at high scale which will be used by open-source Ray users and customers of Anyscale
- Work across the stack integrating Ray Data and LLM engine providing optimizations achieving low cost solutions for large scale ML inference
- Integrate with Open source software like vLLM, work closely with the community to adopt these techniques in Anyscale solutions, and also contribute improvements to open source
- Follow the latest state-of-the-art in the open source and the research community, implementing and extending best practices

We'd love to hear from you if you have

- Familiarity with running ML inference at large scale with high throughput and low latency
- Familiarity with deep learning and deep learning frameworks (e.g. PyTorch)
- Solid understanding of distributed systems, ML inference challenges

Bonus points!

- ML Systems knowledge
- Experience using Ray
- Work closely with community on LLM engines like vLLM, TensorRT-LLM
- Contributions to deep learning frameworks (PyTorch, TensorFlow)
- Contributions to deep learning compilers (Triton, TVM, MLIR)
- Prior experience working on GPUs / CUDA

## Compensation

At Anyscale, we take a market-based approach to compensation. We are data-driven, transparent, and consistent.  As the market data changes over time, the target salary for this role may be adjusted.

This role is also eligible to participate in Anyscale's Equity and Benefits offerings, including the following:

- Stock Options
- Healthcare plans, with premiums covered by Anyscale at 99% for both employees and dependents
- 401k Retirement Plan
- Education & Wellbeing Stipend
- Paid Parental Leave
- Fertility Benefits
- Paid Time Off
- Commute reimbursement
- 100% of in-office meals covered

Anyscale Inc. is an Equal Opportunity Employer. Candidates are evaluated without regard to age, race, color, religion, sex, disability, national origin, sexual orientation, veteran status, or any other characteristic protected by federal or state law.

Anyscale Inc. is an E-Verify company and you may review the Notice of E-Verify Participation https://drive.google.com/file/d/1Kt2S6_k_SjxaEdGowH4rngVdg2ApAQV3/view?usp=sharing and the Right to Work posters in English and Spanish https://drive.google.com/file/d/1K3Nz72xgsU2hngnVUEu53wEeZjbAMbnZ/view?usp=sharing

## About Anyscale

## Company Overview
- **One-liner**: Anyscale provides a production-grade platform for building, running, and scaling data-intensive AI workloads, powered by the open-source Ray framework.
- **Entity Type**: Private (backed by prominent venture investors)
- **Headquarters**: San Francisco, CA, USA (600 Harrison Street, 4th Floor) and Bangalore, India
- **Founded**: 2019
- **Founders**: Co-founders include the creators of Ray from UC Berkeley RISELab (names not explicitly listed in provided sources)

## Core Business
- **Primary industry**: AI Infrastructure / Distributed Computing
- **Target customers**: AI teams building foundation models, data curation pipelines, batch inference, and serving workloads; B2B enterprise and startups
- **Mission**: Make scalable computing effortless  
  **Vision**: Build the future of distributed computing for AI and ML workflows

## Products & Services
- **[Anyscale Platform](https://www.anyscale.com/platform)**: A managed, production-grade platform that runs Ray clusters across any cloud. Includes developer tooling (Workspaces, managed dashboards), cluster orchestration (Jobs & Services, autoscaling, multi-cloud), governance (SSO, SAML, SCIM, budgets), observability (workload-specific dashboards, lineage tracking), and the fully managed Anyscale Runtime.
- **Ray Open-Source Framework**: Although open source and community-driven, Anyscale is built by the creators of Ray and offers the runtime as the core compute engine for its platform.

## Market Standing
- **Valuation/Market Cap**: Not disclosed in provided sources
- **Key Metric**: Total funding not specified in sources; investors include Sequoia Capital, Andreessen Horowitz, NEA, and others (based on investor logos on [about page](https://www.anyscale.com/about)). Ray has exceeded **500 million downloads** and **41K+ GitHub stars**.
- **Notable Investors/Partners**: Sequoia Capital, Andreessen Horowitz, NEA (from company website); partners include AWS, GCP, Azure, CoreWeave, Nebius.
- **Growth Signals**: Employee recommendation rating of **94%**; **4.7 Glassdoor** rating; three offices globally; used by foundation model builders for tasks like embedding generation (80% cheaper), batch inference (3x faster), and training (5x faster).

## Competitive Advantages
- **Ray ecosystem**: Anyscale is built and maintained by the original creators of Ray, the most widely adopted open-source AI compute engine, giving them deep technical expertise and influence on the project’s direction.
- **Multi-cloud orchestration**: Run workloads seamlessly across AWS, GCP, Azure, and specialized GPU clouds without cloud-specific rewrites.
- **Fine-grained hardware allocation and GPU pooling**: Dynamic capacity reallocation maximizes GPU utilization and reduces costs.
- **Developer experience**: Simple Python APIs (e.g., `@ray.remote`) and cluster-backed VS Code/Jupyter workspaces enable scaling from a laptop to a data center without code changes.

## Strategic Focus
- **Current priorities**: Foundation model training and post-training (RLHF, fine-tuning), multimodal data curation, batch embedding generation, and real-time serving. Emphasis on reducing GPU costs and improving developer velocity through unified governance and observability.
- **Direction for growth**: Expanding multi-cloud orchestration, deepening integrations with third-party libraries (vLLM, SGLang, PyTorch, XGBoost), and enabling teams to “unify and govern every team’s AI workloads across clouds.”

## Why Work Here
- **Culture**: Values include “Customer & Community Obsessed,” “LFG” (move fast, push boundaries), “Raise the Bar,” “Take the Longview.”
- **Remote/hybrid/office**: Offices in San Francisco, Palo Alto, and Bangalore. In-office meals (lunch and dinner) and commute reimbursement for Bay Area residents.
- **Benefits**:
  - Health, Vision, Dental (95% covered plans)
  - Fertility benefits (up to $12,500 via Kindbody) and 12 weeks paid parental leave
  - Flexible time off
  - $100/month learning and wellness stipend
  - Paid volunteer time off
  - Mental health support (Rula)
- **Engineering culture**: High autonomy, work on cutting-edge AI infrastructure, close connection to open-source community.

## Sources
1. [anyscale.com](https://www.anyscale.com/)
2. [anyscale.com/about](https://www.anyscale.com/about)
3. [anyscale.com/careers](https://www.anyscale.com/careers)
4. [anyscale.com/platform](https://www.anyscale.com/platform)
5. [jobs.ashbyhq.com/anyscale](https://jobs.ashbyhq.com/anyscale)

## Other roles at Anyscale

- [Software Engineer (Ray Core)](https://feeny.ai/job/software-engineer-ray-core-anyscale-san-francisco-tgvgg1pf4tav) — San Francisco, CA
- [Software Engineer (Ray Data)](https://feeny.ai/job/software-engineer-ray-data-anyscale-san-francisco-4r9rdkv0bpek) — San Francisco, CA
- [IT Specialist](https://feeny.ai/job/it-specialist-anyscale-san-francisco-r91z0szj92w0) — San Francisco, CA
- [Software Engineer, ML Developer Experience](https://feeny.ai/job/software-engineer-ml-developer-experience-anyscale-san-francisco-5htsk54j4ngf) — San Francisco, CA
- [Senior Detection and Response Engineer](https://feeny.ai/job/senior-detection-and-response-engineer-anyscale-san-francisco-pm3xqtnx8mkx) — San Francisco, CA
- [Senior Product Security Engineer](https://feeny.ai/job/senior-product-security-engineer-anyscale-san-francisco-gj30mw06m274) — San Francisco, CA
- [Senior Cloud Security Engineer](https://feeny.ai/job/senior-cloud-security-engineer-anyscale-san-francisco-2g5rb8sm7htx) — San Francisco, CA
- [Compliance Manager](https://feeny.ai/job/compliance-manager-anyscale-san-francisco-hw0ps9rpgzd1) — San Francisco, CA
- [Site Reliability Engineer, Platform Infrastructure (Foundations)](https://feeny.ai/job/site-reliability-engineer-platform-infrastructure-foundations-anyscale-san-qc9t0scbmk32) — San Francisco, CA
- [Software Engineer, Infrastructure](https://feeny.ai/job/software-engineer-infrastructure-anyscale-san-francisco-p3j0kvwghvz4) — San Francisco, CA