Perplexity is looking for an AI Inference Engineer to join their team. The successful candidate will be responsible for developing APIs for AI inference, benchmarking and addressing bottlenecks throughout the inference stack, improving the reliability and observability of systems, and exploring novel research and implementing LLM inference optimisations.
What you'll do
As an AI Inference Engineer at Perplexity, you will have the opportunity to work on large-scale deployment of machine learning models for real-time inference. You will be responsible for developing APIs for AI inference that will be used by both internal and external customers.
- Develop APIs for AI inference that will be used by both internal and external customers
- Benchmark and address bottlenecks throughout our inference stack
- Improve the reliability and observability of our systems and respond to system outages
- Explore novel research and implement LLM inference optimisations
What you need
To be successful in this role, you will need to have experience with ML systems and deep learning frameworks (e.g. PyTorch, TensorFlow, ONNX), familiarity with common LLM architectures and inference optimisation techniques (e.g. continuous batching, quantisation, etc.), and understanding of GPU architectures or experience with GPU kernel programming using CUDA.
- Experience with ML systems and deep learning frameworks (e.g. PyTorch, TensorFlow, ONNX)
- Familiarity with common LLM architectures and inference optimisation techniques (e.g. continuous batching, quantisation, etc.)
- Understanding of GPU architectures or experience with GPU kernel programming using CUDA
