Software Engineer II

Meta Platforms • Redmond, WA

1d • Onsite

About The Position

The Software Engineer II will own and sustain a family of production machine-learning models end to end, including their architecture, checkpoints, evaluation pipelines, serving infrastructure, and failure modes. The role maintains model inference services and evaluation pipelines, integrates models into internal tools and cross-functional workflows through APIs, endpoints, and web UI onboarding, and supports users and tooling owners across domains such as audio engineering, software engineering, research, and program management.

The engineer operates always-on inference capacity by monitoring traffic, resolving throttling, tuning autoscaling, requesting additional capacity, redeploying models, and escalating to platform owners when needed. The role also runs requested analyses, interprets model evaluations, applies minor bug fixes and preprocessing changes, manages version bumps and checkpoint swaps, and serves as on-call for the covered services.

The technology stack includes Python, PyTorch, Bento, Jupyter-style notebooks, internal model-serving and always-on inference capacity, REST- or GraphQL-style endpoints, and a lightweight web UI. The position is onsite in Redmond, Washington, and has a stated duration of six months.

Requirements

• Bachelor's degree in Computer Science, Electrical Engineering, or a related technical field, or equivalent practical experience.
• Proficiency in Python and a deep-learning framework such as PyTorch.
• Knowledge of machine-learning concepts and ML engineering practices.
• Basic knowledge of audio and signal processing.
• Ability to work independently.

Nice To Haves

• Master's or PhD degree in Electrical Engineering, Audio Engineering, Speech or Signal Processing, Acoustics, Computer Science, or a related technical field.
• Two years of hands-on experience deploying and maintaining machine-learning models in production.
• Experience operating production services, including on-call, ticket queues, runbooks, access management, and escalation.
• Working familiarity with audio concepts such as waveforms, sample rates, and spectrograms, sufficient to sanity-check model outputs.
• Excellent communication skills with non-ML audiences, including audio engineers and scientists.
• Experience with internal ML platform tooling stacks.
• Experience with audio, speech, or perceptual quality models, such as MOS prediction.
• Experience developing lightweight web front ends.

Responsibilities

• Own a family of deep-learning models end to end, including architecture, checkpoints, evaluation pipelines, serving infrastructure, and failure modes.
• Integrate models into internal and cross-functional tools and workflows through API/endpoint integration and web UI onboarding.
• Operate always-on model inference capacity by monitoring traffic, resolving throttling, tuning autoscaling, requesting additional capacity, redeploying, and escalating to platform owners as needed.
• Run analyses and interpret model evaluations on request; apply minor bug fixes and preprocessing changes; manage version bumps and checkpoint swaps.
• Communicate with and support model users and tooling owners across domains, including audio engineers, software development engineers, research scientists, and technical program managers.
• Serve as on-call for the covered services.

What This Job Offers

• Career Level: Mid Level