AI Inference Engineer (London)

We are looking for an AI Inference Engineer to join our growing team.

Our current stack includes Python, Rust, C++, PyTorch, Triton, CUDA, and Kubernetes. You will have the opportunity to work on large-scale deployment of machine learning models for real-time inference.

Responsibilities

1. Develop APIs for AI inference used by internal and external customers
2. Benchmark and address bottlenecks in our inference stack
3. Improve system reliability and observability, and respond to outages
4. Explore research and implement optimizations for LLM inference

Qualifications

1. Experience with ML systems and deep learning frameworks (e.g., PyTorch, TensorFlow, ONNX)
2. Familiarity with LLM architectures and inference optimization techniques (e.g., batching, quantization)
3. Experience deploying reliable, distributed, real-time model serving at scale
4. (Optional) Knowledge of GPU architectures or experience with CUDA kernel programming

About Us

At Perplexity, we\’ve experienced significant growth since launching the world\’s first fully functional conversational answer engine over a year ago. Our AI-powered search assistant has reached 10 million monthly active users as of early 2024, with over 1 million app installations across iOS and Android. In 2023, we served over 500 million queries globally.

To support our expansion, we\’ve secured substantial funding from top investors. In January 2024, we raised $73.6 million in Series B led by IVP, with participation from NVIDIA, Jeff Bezos\’ fund, NEA, Databricks, and others. In April 2024, we raised an additional $62.7 million in Series B1, valuing the company at over $1 billion.

Our notable investors include IVP, NEA, Jeff Bezos, NVIDIA, Databricks, Bessemer Venture Partners, Elad Gil, Nat Friedman, Naval Ravikant, Tobi Lutke, among others.

Final offer amounts depend on experience and expertise and may vary from listed figures.

Benefits include comprehensive health, dental, and vision insurance, a 401(k) plan, and potential equity as part of the compensation package.

#J-18808-Ljbffr