> Markdown version of [/jobs/ext/4647262-inference-systems-engineer](https://www.wearedevelopers.com/jobs/ext/4647262-inference-systems-engineer). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Inference Systems Engineer - **Company:** MODULAR AI, INC - **Location:** Beverly Hills, CA, United States - **Experience:** Expert - **Salary:** $198,000 - $242,000 - **Contract:** Permanent contract - **Skills:** Application Programming Interfaces (APIs), Artificial Intelligence, Systems Engineering, Cloud Computing, Data Transmissions, Extract Transform Load (ETL), Data Structures, Distributed Systems, Data Flow Control, Python (Programming Language), Machine Learning, Open Source Technology, Performance Tuning, Posix, Software Systems, System Programming, Large Language Models, Concurrency, Caching, Non-Uniform Memory Access, AI Platforms, SGLang, Machine Learning Operations, VLLM - **Published:** November 9, 2026 - **Apply:** https://www.careerbuilder.com/job-details/inference-systems-engineer-beverly-hills-ca--23e6897c-b834-4b10-806c-1ed715a1b819 ## About the Role Systems Engineering, Performance Tuning/Optimization, Artificial Intelligence (AI), Caching, Onboarding, Distributed Computing, Concurrency, Cloud Computing, Team Lead/Manager, Open Source, * 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 whats 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. ## Description 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 teams 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 tomorrows 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.