Software Engineer - Model API's

Baseten powers inference for dynamic AI companies, enabling them to bring cutting‑edge models into production by combining applied AI research, flexible infrastructure, and developer tooling.

THE ROLE

Baseten’s Model Performance (MP) team ensures the models running on our platform are fast, reliable, and cost‑efficient. As part of that team, you’ll focus on Model APIs — the infrastructure powering hosted API endpoints for the latest open‑source models. This work spans distributed systems, model serving, and developer experience, helping to define how developers interact with AI models at scale.

RESPONSIBILITIES

Design, build, and operate the Model APIs surface with focus on advanced inference capabilities, such as structured outputs, tool/function calling, and multi‑modal serving. Profile and optimize TensorRT-LLM kernels, analyze CUDA kernel performance, implement custom CUDA operators, and tune memory allocation patterns for maximum throughput. Optimize communication patterns across multi‑GPU setups and productionize performance improvements across runtimes, including speculative decoding, guided generation, and custom scheduling and routing algorithms for high‑performance serving. Build comprehensive benchmarking frameworks that measure real‑world performance across different model architectures, batch sizes, sequence lengths, and hardware configurations. Implement deep observability, including metrics, traces, and logs, and create repeatable benchmarks to measure speed, reliability, and quality. Implement platform fundamentals such as API versioning, validation, usage metering, quotas, and authentication. Collaborate closely with other teams to deliver robust, developer‑friendly model serving experiences.

REQUIREMENTS

3+ years of experience building and operating distributed systems or large‑scale APIs. Proven track record of owning low‑latency, reliable backend services, including rate‑limiting, authentication, quotas, metering, and migrations. Infra instincts with performance sensibilities: profilers, tracers, capacity planning, and SLO management. Comfortable debugging complex systems, from runtime internals to GPU execution traces. Strong written communication skills, able to produce clear design documents and collaborate across functions.

NICE TO HAVE

Experience with LLM runtimes such as vLLM, SGLang, TensorRT‑LLM, or contributions to open‑source inference engines. Knowledge of Kubernetes, service meshes, API gateways, or distributed scheduling. Background in developer‑facing infrastructure or open‑source APIs. A preference for infra‑leaning generalists; ML experience is a plus but not required.

BENEFITS

Competitive compensation package. Opportunity to be part of a rapidly growing startup in an exciting engineering field. An inclusive and supportive work culture that fosters learning and growth. Exposure to a variety of ML startups, offering unparalleled learning and networking opportunities.

COMPENSATION

$150,000 – $230,000 • Offers Equity Competitive compensation. We aim to provide 90th percentile (or better) salaries and equity grants for every team member commensurate with their experience. 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. #J-18808-Ljbffr Baseten