LinkedIn is seeking a Senior Software Engineer to join their AI Platform team, focusing on scaling LinkedIn's AI model training, feature engineering and serving infrastructure. This is an exciting opportunity to work at the world's largest professional network, helping build systems that handle hundreds of billions of parameters models and large-scale feature engineering infrastructure for all AI use cases.
The role involves working with cutting-edge AI technologies, from recommendation models to large language models and computer vision models. You'll be optimizing performance across algorithms, AI frameworks, data infrastructure, compute software, and hardware to maximize the potential of LinkedIn's GPU fleet comprising thousands of latest GPU cards.
As a senior engineer, you'll collaborate with the open source community, with many team members being active contributors to projects like TensorFlow, Horovod, Ray, vLLM, Huggingface, and DeepSpeed. The work spans multiple critical areas:
In Model Training Infrastructure, you'll build next-gen training infrastructure, optimize data I/O, resolve issues in popular open source libraries, enable distributed training for massive models, and provide advanced support for internal AI teams. You'll also work on containerized pipeline orchestration and maintain deep learning frameworks.
The Feature Engineering aspect involves creating and managing features within online, offline, and nearline environments at scale, processing millions of QPS and multi-terabytes of data. You'll work with technologies like Spark, Beam, and Flink to transform raw data into valuable feature insights.
For Model Serving Infrastructure, you'll develop low latency applications serving large & complex models, implement GPU-based inference, and perform CUDA-level optimizations. The role requires handling significant scale - 10s of thousands of QPS, multiple terabytes of data, and billions of model parameters.
The position offers competitive compensation, comprehensive benefits, and the opportunity to work in a hybrid environment, combining remote work with office time. LinkedIn's culture emphasizes trust, connection, and career growth, making it an ideal place for talented engineers looking to make a significant impact in the AI infrastructure space.