Inference Systems Engineer

About Modular At Modular, we’re on a mission to revolutionize AI infrastructure by systematically rebuilding the AI software stack from the ground up. Our team, made up of industry leaders and experts, is building cutting-edge, modular infrastructure that simplifies AI development and deployment. By rethinking the complexities of AI systems, we’re empowering everyone to unlock AI’s full potential and tackle some of the world’s most pressing challenges. If you’re passionate about shaping the future of AI and creating tools that make a real difference in people’s lives, we want you on our team. You can read about our culture and careers to understand how we work and what we value. About the role: ML developers today face significant friction in taking trained models into deployment. They work in a highly fragmented space, with incomplete and patchwork solutions that require significant performance tuning and non-generalizable, model-specific enhancements. At Modular, we are building the Modular platform: a next generation AI platform that will radically improve the way developers build and deploy AI models. State-of-the-art inference is a fast moving target - every few months brings new model architectures, new attention variants, new parallelism strategies, and new optimization techniques (e.g. new variants of disaggregation, speculative decoding, hierarchical KV caching, constrained decoding, MoE routing, and more). Building each feature right in isolation is already a challenge, but designing for clean composability and long tail reliability brings it to another level. LOCATION: Candidates based in the United States are welcome to apply. To support growth and collaboration, those in earlier career stages work in a hybrid capacity at our Los Altos, CA. More senior staff can work out of our office in Los Altos, CA or remotely from home. Onboarding for new hires is conducted in-person in our Los Altos, CA office. What you will do: This team's job is to identify the opportunities for unifying structures underneath today’s inference features, and turn them into the robust and flexible distributed-systems abstractions and building blocks to make tomorrow's features ship faster and more robustly. Responsibilities would include: Leading cross-team architecture-level decisions on concurrency, data movement, and system boundaries in a fast-moving in-house software stack spanning from the metal to the cloud. Developing flexible and extensible interfaces for open-source model developers and community contributors that are not just enjoyable to use, but implicitly promote best practices. Designing highly modular systems with clear contracts to create components with unambiguous ownership, testability, and scaffolding for robust agentic development. What you bring to the table: 5+ years of systems programming experience with a focus on performance, concurrency, and distributed architectures Strong instinct for API and abstraction design, and the ability to present a strong case for design proposals Comfortable working in Python, Rust, Mojo, or similar (in the agentic-coding era, we believe deep understanding of software systems supersedes knowing language syntax) Intuition and ability to reason about pathological performance bottlenecks in complex systems, and translate that into concrete diagnostics and solutions Demonstrated ownership of software solutions from implementation through production support. You bring war stories from learning the hard way why defensive engineering is worth the extra investment. Genuine interest in the research literature and solid instincts for what's worth building Helpful Experience Experience under the hood deep inside a high-performance ML inference system (vLLM, SGLang, TRT-LLM, etc.) Broad systems programming experience: lock-free and wait-free data structures, POSIX APIs and architecture, memory-layout aware optimization, NUMA-aware design, zero-copy transport, etc. Experience with graph-based (dataflow, actor) programming models and runtimes Experience with GPU or accelerator programming, especially optimizing around async scheduling and data transfer. What Modular brings to the table: Amazing Team. We are a progressive and agile team with some of the industry’s best engineering and product leaders. World-class Benefits. In order to attract the best, we need to offer the best. Premier insurance plans, up to 5% 401k matching, flexible paid time off, and more are available to you! Please note that specific benefit packages may vary based on your location. Competitive Compensation. We offer very strong compensation packages, including stock options. We want people to be focused on their best work and believe in tailoring compensation plans to meet the needs of our workforce. Team Building Events. We organize regular team onsites and local meetups in Los Altos, CA as well as different cities. Traveling 2-4 times a year is expected for all roles. Working at Modular will enable you to grow quickly as you work alongside incredibly motivated and talented people who have high standards, possess a growth mindset, and a purpose to truly change the world. The estimated base salary range for this role to be performed in the US, regardless of the state, is $198,000.00 - $242,000.00 USD . The salary for the successful applicant will depend on a variety of permissible, non-discriminatory job-related factors, which include but are not limited to education, training, work experience, business needs, or market demands. This range may be modified in the future. The total compensation for a candidate will also include annual target bonus, equity, and benefits, with equity making up a significant portion of your total compensation. For candidates who fall outside of the listed requirements, we nevertheless encourage you to apply as we may have openings that are lower/higher level than the ones advertised.