Lead Machine Learning Engineer, MLOps

What you'll do

• Build and maintain pipelines for distributed model training on GPU-enabled clusters.
• Develop pipelines for high-throughput, real-time and batch model inference.
• Implement quantization techniques to deploy large language models efficiently.
• Manage and optimize vector databases for advanced AI applications.
• Establish monitoring and observability pipelines to ensure system health and performance.
• Integrate new technologies and improve existing infrastructure with cross-functional teams.
• Define scalable and performant technical solutions with product and architecture teams.

What we're looking for

• BS in Computer Science or related Engineering with 6+ years of experience or MS degree with 4+ years of experience.
• Extensive experience in Python and cloud computing, preferably AWS.
• Experience in systems engineering fundamentals including caching, CUDA, autoscaling, high throughput, and low latency.
• Understanding of quantization techniques such as PTQ and AWQ for accelerating LLM inference.
• Operational experience in big data/ML tools such as Ray, DuckDB, Spark, and vllm/SGLang.
• Experience in monitoring and observability tools to monitor model input/output and feature stats.
• Experience with recommendation and personalization systems (preferred).
• Experience with containers (Docker, Kubernetes, ECS) and DAG orchestration (Airflow, Kubeflow) (preferred).