Developing and maintaining prompt processing and tokenization pipelines that prepare inference requests for efficient model execution.
Implementing request routing, scheduling, and batching logic that optimizes throughput and latency across concurrent inference workloads.
Contributing to the integration of new model architectures and serving backends into the runtime framework.
Writing well-tested, well-documented code and participating in code reviews to maintain high engineering standards across the inference stack.
Supporting operational readiness through monitoring, debugging, and performance analysis of runtime components.

Have relevant experience and a Bachelor's degree or its equivalent in Computer Science or a related field.
Demonstrate proficiency in Python and at least one systems programming language such as C++, Go, or Rust.
Show understanding of natural language processing concepts including tokenization, encoding, and text processing pipelines.
Have familiarity with AI inference, model serving, or LLM deployment including inference frameworks (TensorRT, vLLM, TorchServe, Triton).
Demonstrate experience building high-throughput, low-latency data processing systems or services.
Show familiarity with Linux systems, containerized environments, and profiling or debugging tools.
Demonstrate a keen willingness to learn and grow within the AI inference and model serving field.

Senior Software Engineer

Key skills