onsite
Staff / Principal Machine Learning Engineer, Serving - Inworld
ML Engineer
Lead the design and deployment of cutting‑edge real‑time voice models, driving performance, scalability, and reliability across consumer‑facing AI applications using advanced ML, deep learning, and cloud technologies.
About the role
Key Responsibilities
- Architect and implement end‑to‑end serving pipelines for large‑scale, low‑latency voice models.
- Collaborate with research teams to translate novel algorithms into production‑ready systems.
- Optimize model inference on GPU/CPU clusters, ensuring high throughput and minimal latency.
- Design monitoring, logging, and automated retraining workflows to maintain model quality.
- Mentor junior engineers and foster a culture of continuous improvement and knowledge sharing.
Requirements
- 10+ years of experience in machine learning engineering, with a focus on serving and production systems.
- Deep expertise in PyTorch/TensorFlow and experience deploying models at scale on AWS or GCP.
- Strong background in NLP and speech‑recognition technologies.
- Proficiency in distributed systems, container orchestration (Kubernetes), and CI/CD pipelines.
- Excellent communication skills and a proven track record of leading technical initiatives.
Skills
machine learningdeep learningpytorchtensorflownlp