Software Engineer- Inference Performance

THE ROLE

We're looking for inference performance engineers who want to make the world's most demanding AI workloads run faster and more efficiently. You'll work across the stack, from the inference engine and runtime through scheduling, serving, and routing. Along the way you'll apply techniques like prefill/decode disaggregation, speculative decoding, and KV-cache management. You'll reason from first principles about where time and memory go, find what's holding performance back, and close the gap. Your work directly impacts how fast our customers' models run and how efficiently we serve them. This role is ideal for someone who thrives in a fast-paced startup environment and is eager to make significant contributions to the exciting field of LLM inference.

EXAMPLE INITIATIVES

You'll get to work on these types of projects as an Inference Performance engineer

• Agentic Kernels in Production
• How we built the new fastest API for GLM-5.2
• Live draft model training for speculative decoding
• Making Kimi K3 Tokenization 18x faster
• The Baseten Inference Stack
• Driving model performance optimization

RESPONSIBILITIES

• Implement and productionize cutting-edge inference techniques, working deep in runtime internals. That includes quantization, speculative decoding, KV-cache reuse, chunked prefill, LoRA, guided generation for structured outputs, and custom scheduling and routing algorithms.
• Profile and optimize inference end to end, from kernel launch overhead and memory layout up to request scheduling, prefill/decode disaggregation, and cache-aware routing. Run cross-layer investigations, such as tracing a tail-latency regression from request timing through routing and batching down to a kernel.
• Turn performance into cost savings. Improve tokens per GPU-hour, raise utilization, and give customers and internal teams clear latency/throughput/cost tradeoffs.
• Bring up and tune new model architectures on new hardware quickly, often in the same week they're released.
• Build benchmarking frameworks that measure real-world performance across model architectures, batch sizes, sequence lengths, and hardware configurations.
• Contribute upstream to open-source inference engines (vLLM, SGLang, TensorRT-LLM), and partner closely with model, infrastructure, and customer-facing teams to ship wins.

REQUIREMENTS

• Bachelor's, Master's, or Ph.D. degree in Computer Science, Engineering, Mathematics, or related field.
• Experience with one or more general-purpose programming languages, such as Python or C++.
• Familiarity with LLM optimization techniques (e.g., quantization, speculative decoding, continuous batching).
• Strong familiarity with ML libraries, especially PyTorch, TensorRT, or TensorRT-LLM.
• Demonstrated interest and experience in LLMs.
• Deep understanding of GPU architecture.

NICE TO HAVE

• Proficiency in enhancing the performance of software systems, particularly in the context of large language models (LLMs)
• Contributed to vLLM, SGLang, TensorRT-LLM, or another inference engine.
• Worked on large-scale distributed serving: autoscaling, load balancing, multi-region or multi-cloud capacity.
• Written or optimized GPU kernels (CUDA, Triton, CUTLASS, or similar)
• Worked on quantization (FP8/FP4, AWQ, GPTQ) or speculative decoding in production.
• Deep understanding of software engineering principles and a proven track record of developing and deploying AI/ML inference solutions.