Senior Researcher - Efficient AI

Microsoft•Redmond, WA
•$119,800 - $261,000

About The Position

Microsoft’s applied research team advances efficiency across the AI stack, including models, machine-learning frameworks, cloud infrastructure, and hardware. The team works with research and product groups across Microsoft to drive mid- and long-term product innovation. Its work is communicated through internal technical reports, academic publications, open-source releases, and patents, and researchers take ideas from research through prototyping, validation, and production with a focus on real-world impact. The Senior Researcher will work across the full stack, from large-scale serving systems to hardware- and kernel-level optimizations. The role explores algorithmic, systems, and hardware/software co-design techniques, including batching, routing, scheduling, caching, endpoint configuration, and GPU architecture-aware optimizations. It requires end-to-end ownership of identifying high-impact problems and taking research ideas through prototyping, validation, and deployment to deliver measurable customer impact.

Requirements

  • Doctorate in a relevant field, or a master’s degree in a relevant field and 3+ years of related research experience, or a bachelor’s degree in a relevant field and 4+ years of related research experience, or equivalent experience.
  • Ability to meet Microsoft, customer, and/or government security screening requirements, including passing the Microsoft Cloud Background Check upon hire or transfer and every two years thereafter.

Nice To Haves

  • Demonstrated experience designing and optimizing efficient inference systems, combining algorithmic optimization, parallel computing, and request orchestration under strict SLO constraints with knowledge of attention and KV-cache optimizations, batching and scheduling strategies, and cost-aware deployment.
  • 3+ years of experience with machine-learning frameworks such as PyTorch or TensorFlow and inference-serving frameworks such as vLLM, Triton Inference Server, TensorRT-LLM, ONNX Runtime, Ray Serve, or DeepSpeed-MII.
  • 3+ years of experience in GPU programming and optimization, with expert knowledge of CUDA, ROCm, Triton, PTX, CUTLASS, or similar GPU programming frameworks.
  • Proficiency in C++ and Python for high-performance systems, including code quality, profiling, and debugging skills.
  • Research impact through publications and/or patents, together with hands-on experience taking research ideas through execution and delivery in production.

Responsibilities

  • Formulate, develop, and evaluate algorithmic and system-level approaches for end-to-end AI serving, using analytical modeling and large-scale measurements to study token-level and tail latency, throughput per dollar, cold-start behavior, warm-pool strategies, and capacity planning under multi-tenant SLOs and variable sequence lengths.
  • Design and experimentally evaluate endpoint configurations and execution policies, including batching, routing, scheduling, tensor and pipeline parallelism, quantization and precision profiles, speculative decoding, and chunked or streaming generation.
  • Drive promising approaches through robust rollout and validation into production.
  • Collaborate with model, kernel, compiler, and hardware teams on hardware- and kernel-aware optimization, aligning serving algorithms with attention and KV innovations and accelerator capabilities.
  • Build and benchmark experimental prototypes and large-scale measurements to validate research ideas and advance them toward production readiness.
  • Produce technical documentation, design reviews, and operational playbooks.
  • Publish research results, file patents, and contribute to open-source systems and serving frameworks where appropriate.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service