Vllm Jobs in Utah (NOW HIRING)

Smule has been on a mission to bring the world together through music since 2008. Music is much more than listening… it's about creating, sharing, discovering, participating, and connecting with people. With dozens of millions of monthly active users creating over 20 million songs every day, Smule is connecting people all over the world through the joy of making music and transforming the music landscape from one of passive listening to collaborative creative expression and active engagement.

We are looking for a Machine Learning Engineer to own the end-to-end lifecycle of ML models in production at Smule, from training and optimization through deployment, monitoring, and iteration. You will work closely with research scientists to bring models off the bench and into scalable, reliable systems that serve millions of users. The ideal candidate is a strong engineer first, with deep practical knowledge of ML systems, a passion for reliability, and an eye for performance.

We strongly encourage candidates with non-traditional backgrounds to apply. If your path into ML engineering came through backend systems, DevOps, audio software, data engineering, or another field, we want to hear from you.

• Design, build, and maintain production ML pipelines encompassing data ingestion, feature engineering, model training, evaluation, and deployment.
• Optimize models for production constraints including latency, throughput, memory footprint, and cost, using techniques such as quantization, distillation, pruning, and efficient serving architectures.
• Implement robust monitoring, alerting, and observability for deployed models, covering data drift, prediction quality, and system health.
• Collaborate with research scientists to integrate new model architectures and training techniques into production systems with minimal friction.
• Build and improve CI/CD pipelines for ML, including automated testing, validation gates, and staged rollouts.
• Manage compute infrastructure and costs, making informed tradeoffs between performance, reliability, and budget.

• Degree (B.S., M.S., or Ph.D.) in Computer Science, Software Engineering, Electrical Engineering, or a related technical discipline, or currently pursuing one.
• Strong proficiency in Python and experience with deep learning serving (TorchServe, Triton, vLLM, or equivalent).
• Solid understanding of systems engineering: networking, storage, containerization, orchestration, and monitoring.
• Ability to reason about tradeoffs between latency, throughput, cost, and model quality.

• Experience serving large language models or other generative models at scale.
• Familiarity with audio/music processing pipelines and real-time inference constraints.
• Experience with Bayesian optimization, bandit algorithms, or adaptive experimentation platforms.
• Contributions to open-source ML infrastructure projects.

Smule is an Equal Opportunity Employer and considers all qualified applicants without regard to race, color, religion, sex, gender identity or expression, sexual orientation, national origin, ancestry, age, disability, medical condition, genetic information, marital status, military or veteran status, or any other protected characteristic under federal, state, or local law.

We are committed to creating an inclusive environment for all employees and applicants. If you require a reasonable accommodation during the application or interview process, please let us know.