--- title: 'Engineering Manager Runtime - Storage at Baseten' canonical: 'https://feeny.ai/job/engineering-manager-runtime-storage-baseten-san-francisco-tj58p3wmtdwz' type: 'job' last_seen: '2026-10-18' --- # Engineering Manager Runtime - Storage at Baseten - **Company:** [Baseten](https://feeny.ai/companies/baseten) - **Location:** San Francisco, CA - **Compensation:** $165k–$330k - **Employment:** full-time - **Work type:** hybrid - **Posted:** 2026-10-15 - **Last confirmed live:** 2026-10-18 - **Apply:** https://jobs.ashbyhq.com/baseten/b6ef1aed-8e71-4b31-9cfe-e95d793c8604 ## Job description ## ABOUT BASETEN Baseten powers mission-critical inference for the world's most dynamic AI companies, like Cursor, Notion, OpenEvidence, Abridge, Clay, Gamma, and Writer. By uniting applied AI research, flexible infrastructure, and seamless developer tooling, we enable companies operating at the frontier of AI to bring cutting-edge models into production. We're growing quickly and recently raised our [$1.5B Series F](https://www.baseten.co/blog/announcing-our-series-f/), led by Altimeter Capital, Conviction Partners, and Spark Capital. Join us and help build the platform engineers turn to ship AI products. ## THE ROLE Container runtimes were designed for general-purpose software workloads. AI inference is not a general-purpose workload. Running large models at production scale exposes cracks in every layer of the container stack: runtimes unaware of GPU memory constraints, images that take minutes to pull when a model needs to scale to thousands of replicas, and isolation mechanisms that weren’t designed for the multi-tenant serving environments that production AI requires. The tools the industry has relied on for a decade weren’t built for this, and patching around those limitations at higher layers only goes so far. Baseten owns the entire pipeline, from the moment a developer pushes a model to the moment a request gets a response. That vertical ownership means we can fix these problems at the root. The Runtime Fabric team is doing exactly that: purpose-building the container runtime and storage layers for AI inference workloads, led by some of the world’s top containerd maintainers. As Engineering Manager for Storage Products on the Runtime Fabric team, you will lead the engineers who build and run the storage products behind that stack: the Baseten Delivery Network (BDN), which sits in the cold start path of every model on the platform, the snapshotters and filesystems that expose model weights and container images to a running container, and the storage that model deployment and training need next. The team is advancing the next generation of caching for inference workloads, from the origin tier to the GPU host. You will own reliability for the area as a measured outcome, report to the head of Runtime Fabric, and stay close to the code through design and code review. If you’ve managed systems engineers and have hands-on experience with caching, content-addressable storage, or distributed filesystems, we’d love to talk. ## EXAMPLE INITIATIVES - https://www.baseten.co/blog/how-the-baseten-delivery-network-bdn-makes-cold-starts-fast/ - Extending BDN from model weights to container image layers, training checkpoints, and deployment artifacts - Lazy-loading snapshotters and block-level delivery (EROFS, FUSE, ublk) so a container can start before the full image or model has arrived ## RESPONSIBILITIES ## Team Leadership and Culture - Hire and grow a team of 5 to 10 systems engineers with storage, caching, and Linux expertise - Run the team’s planning and delivery: scope work against the Runtime Fabric roadmap, set priorities, and ship on a predictable cadence - Provide regular coaching, feedback, and career development support to your direct reports - Own on-call health for the team’s services, including escalation paths and follow-through on incidents Technical Direction - Guide the architecture and evolution of the Baseten Delivery Network: the tiered caching and weight delivery product that makes cold starts 2-3x faster and eliminates thundering herd failures during burst scaling events - Shape storage products tailored to Baseten’s workloads: extend BDN from model weights to container images, training checkpoints, and deployment artifacts, and define the interfaces that model deployment, training, and customers use to reach them - Oversee the on-host side of delivery: lazy-loading snapshotters, EROFS and overlayfs layouts, and block-level delivery (FUSE, ublk) for multi-gigabyte files - Own reliability of the delivery path as a measured outcome: end-to-end instrumentation from snapshotter initialization to first inference request, targets for cold start and cache behavior, tolerance for failing upstream registries and object stores, and safe rollout of changes to a path every customer depends on - Make the delivery path work across heterogeneous clusters and cloud providers, each with its own object store and network - Review designs and code across the area, and take on hands-on work where it unblocks the team - Champion the team’s contributions back to containerd and the snapshotter ecosystem alongside the maintainers on the Runtime Fabric team Cross-Functional Partnership - Act as the point of contact for storage across Baseten, ensuring model deployment, training, and platform teams have the integration support they need - Optimize requirements for the underlying storage platforms with the infrastructure team: object storage, local NVMe and block storage, and network bandwidth per cluster, so that capacity and provider decisions account for what the delivery path needs - Manage the team’s dependencies in both directions: sequence work that model deployment, training, and infrastructure teams block on, and negotiate interfaces and timelines with the teams and upstream projects the storage path depends on - Work with the head of Runtime Fabric and product stakeholders to prioritize storage investments based on customer impact and infrastructure reliability - Communicate team progress, technical trade-offs, and incidents clearly to the team and to leadership ## REQUIREMENTS - Experience managing a team of engineers in a systems, infrastructure, or storage context, including hiring and performance management [TODO: confirm whether a tech lead stepping into management qualifies] - Hands-on background in distributed storage systems, content-addressable storage, or large-scale caching infrastructure - Strong systems programming background in Go, Rust, and/or C/C++, with the ability to engage credibly in code reviews and architectural discussions - Working knowledge of the Linux storage stack: filesystems, the page cache, block devices, and mounts - Understanding of how container images are structured, stored, and delivered at scale - Strong written and verbal communication skills, with the ability to influence without authority across teams ## NICE TO HAVE - Contributions to containerd/containerd, snapshotter projects (stargz, soci, nydus, overlaybd), distribution/distribution, or closely related open-source projects - Familiarity with lazy-loading snapshotters or peer-to-peer image distribution - Experience with EROFS, FUSE, ublk, or io_uring - Experience building or operating CDN, object storage, or large-scale caching infrastructure - Experience running storage services on Kubernetes ## BENEFITS - Competitive compensation, including meaningful equity - (U.S. only) 100% coverage of medical, dental, and vision insurance for employee and dependents - Flexible PTO policy including company wide Winter Break (our offices are closed from Christmas Eve to New Year's Day!) - Paid parental leave - Fertility and family-building stipend through Carrot - (U.S. only) Company-facilitated 401(k) - Exposure to a variety of ML startups, offering unparalleled learning and networking opportunities. Apply now to embark on a rewarding journey in shaping the future of AI! If you are a motivated individual with a passion for machine learning and a desire to be part of a collaborative and forward-thinking team, we would love to hear from you. At Baseten, we are committed to fostering a diverse and inclusive workplace. We provide equal employment opportunities to all employees and applicants without regard to race, color, religion, gender, sexual orientation, gender identity or expression, national origin, age, genetic information, disability, or veteran status. We are an Equal Opportunity Employer and will consider qualified applicants with criminal histories in a manner consistent with applicable law (by example, the requirements of the San Francisco Fair Chance Ordinance, where applicable). ## About Baseten ## Company Overview - **One-liner**: Baseten is an AI infrastructure platform that provides high-performance inference infrastructure for deploying, optimizing, and managing AI models in production. - **Entity Type**: Private (Series F) - **Headquarters**: San Francisco, California, United States - **Founded**: 2019 - **Founders**: Tuhin Srivastava (CEO), Amir Haghighat (CTO), Phil Howes (Co-Founder & Chief Scientist) ## Core Business - **Primary industry/industries**: AI Infrastructure / Cloud Computing / MLOps - **Target customers**: B2B, targeting AI-native companies, enterprises, and developers building and deploying large-scale AI applications. Notable customers include Abridge, Cursor, Lovable, Notion, and OpenEvidence. - **Mission or purpose statement**: Provide the tooling, expertise, and hardware needed for teams to bring performant AI products to market as quickly and reliably as possible. The company's core belief is that "inference is everything" and that the future of AI will consist of millions of specialized models embedded into every product and workflow. ## Products & Services - **Baseten Cloud**: A fully-managed, global deployment platform for AI models. Provides out-of-the-box performance optimizations, 99.99% uptime, and massive horizontal scale. Supports single-tenant and self-hosted (hybrid) deployments. - **Baseten Inference Stack**: The proprietary, underlying technology that powers the platform. Includes custom model runtimes (LLMs, embeddings, voice AI, image generation), advanced caching, custom kernels, and cutting-edge performance research. Claims 2x higher throughput and 10% lower latency for embeddings (BEI). - **Baseten Chains**: Enables granular hardware and autoscaling for compound AI systems, reportedly powering 6x better GPU usage and cutting latency in half. - **Frontier Gateway (Pre-optimized Model APIs)**: Allows users to instantly test and deploy pre-optimized versions of the latest open-source, custom, and fine-tuned models (e.g., Qwen, DeepSeek, GLM, gpt-oss). - **Forward Deployed Engineering (FDE)**: A service offering where Baseten engineers work side-by-side with key customers to build, optimize, and scale their models from prototype to production. - **Training on Baseten**: Allows users to train models and deploy them in one click on the inference-optimized infrastructure. - **Monetization API**: An inference API that allows model developers to monetize their models. ## Market Standing - **Valuation/Market Cap**: Not privately disclosed, but the company has raised a total of **$585M** in funding. - **Key Metric**: Annual revenue of **$7.0M** (as per LinkedIn). Total funding of **$585M**. - **Notable Investors/Partners**: IVP, Spark Capital, Bond, CapitalG, South Park Commons, Greylock. - **Growth Signals**: - Announced a **Series F** funding round (details not fully public in search results). - **Massive headcount growth**: 224.4% year-over-year, now employing 201 people. - **LinkedIn follower growth**: 199.9% year-over-year. - **Active job postings**: 112 open roles. - Acquired the company **Parsed**. - Backed by high-profile institutional investors including CapitalG (Alphabet's growth fund) and IVP. ## Competitive Advantages - **High-Performance Inference Stack**: A proprietary, deeply optimized stack focusing on ultra-low latency and high throughput for the most demanding Gen AI workloads (voice AI, real-time streaming, complex compound AI systems). - **Customer Obsession & Forward Deployed Engineering**: A hands-on, consulting-style approach with their FDE team, which builds deep, sticky relationships with high-value customers like Abridge and Notion. - **Global & Hybrid Cloud Flexibility**: Offers both fully-managed cloud and self-hosted deployments within customer VPCs, providing scalability and security for enterprises with strict data governance requirements. - **Founding Team's Deep Technical Credibility**: Built by former researchers and engineers who experienced the "deployment hell" of AI systems firsthand, giving them deep empathy and expertise in the problem they are solving. ## Strategic Focus - **Dominating the "Inference-as-a-Service" Market**: The company's core thesis is that inference will become the largest market ever created, and they are building the infrastructure to power it. - **Scaling for High-Volume, Mission-Critical Workloads**: Focus on reliability, performance, and cost-efficiency for customers who cannot afford downtime or latency (e.g., AI phone calls, real-time translation). - **Deepening the Technical Stack**: Continuously investing in performance research (custom kernels, new decoding techniques) and expanding capabilities into new areas like voice AI and audio streaming. - **Aggressive Hiring**: With 112 open positions and massive YoY growth, scaling the engineering, sales, and operations teams is a clear priority. ## Why Work Here - **Hard Technical Problems**: Engineers work on the most challenging problems in modern infrastructure—model serving, low-level GPU optimization, networking, distributed systems, and observability. This is a high-agency, high-impact engineering environment. - **High Growth Trajectory**: The company is experiencing explosive growth (224% headcount increase, active hiring). This offers significant career acceleration and ownership opportunities. - **Strong Engineering Culture**: Founded by engineers, for engineers. The culture emphasizes "first-principles thinking across the entire stack" and a "customer-obsessed" mindset. The employer rating on compensation, culture, and work-life balance is rated highly (5.0). - **Top-Tier Team & Investors**: The team has strong talent density with hires from Meta, Stripe, Google, NVIDIA, and Databricks. Being backed by top-tier VCs provides stability and a clear long-term vision. - **Hybrid/In-Office**: Based in San Francisco with a strong in-person or hybrid culture common for fast-moving infrastructure startups. ## Sources 1. [Company Website](https://www.baseten.co/) 2. [Careers Page](https://www.baseten.co/resources/careers/) 3. [About Us (Team)](https://www.baseten.co/about-us/) 4. [LinkedIn Company Profile](https://www.linkedin.com/company/baseten) 5. [Ashby Careers Portal](https://jobs.ashbyhq.com/baseten) ## Other roles at Baseten - [Product Marketing Manager, Partnerships](https://feeny.ai/job/product-marketing-manager-partnerships-baseten-san-francisco-nq8djv2cchyf) — San Francisco, CA - [Partner Enablement Lead](https://feeny.ai/job/partner-enablement-lead-baseten-san-francisco-hnn1ex9bg330) — San Francisco, CA - [Sales Manager - Enterprise (New York)](https://feeny.ai/job/sales-manager-enterprise-new-york-baseten-new-york-5tyvjykwwgvp) — New York, NY - [GRC Manager](https://feeny.ai/job/grc-manager-baseten-san-francisco-h4rsmvjx5r79) — San Francisco, CA - [Post-Training Applied Researcher](https://feeny.ai/job/post-training-applied-researcher-baseten-san-francisco-rkqr55d1q922) — San Francisco, CA - [Engineering Manager - Inference Performance](https://feeny.ai/job/engineering-manager-inference-performance-baseten-san-francisco-g288gz5d5c72) — San Francisco, CA - [Solutions Architect, EMEA](https://feeny.ai/job/solutions-architect-emea-baseten-remote-7wm26ab3zv3k) - [Software Engineer - Inference Platform](https://feeny.ai/job/software-engineer-inference-platform-baseten-san-francisco-c8ft1e43rhsm) — San Francisco, CA - [Software Engineer - Inference Performance](https://feeny.ai/job/software-engineer-inference-performance-baseten-san-francisco-z5nwnfabvs6n) — San Francisco, CA - [Marketing Recruiter](https://feeny.ai/job/marketing-recruiter-baseten-new-york-12dbt8dhg270) — New York, NY