Research Scientist / Research Engineer, Inference Systems

Job description

About Bitdeer: Bitdeer is a world-leading technology company for Bitcoin mining and AI cloud. Bitdeer is committed to providing comprehensive Bitcoin mining solutions for its customers. Apart from designing industry-leading ASIC chips and manufacturing mining rigs, the Group handles complex processes involved in computing across the value chain. This includes equipment procurement, transport logistics, datacenter design and construction, equipment management, and network and facility operations. Bitdeer also offers advanced cloud capabilities to customers with a high demand for artificial intelligence. Headquartered in Singapore, Bitdeer operates globally with a diversified 3 GW energy portfolio, and deploys Bitcoin mining and HPC datacenters in the United States, Bhutan, Norway, Canada, Malaysia, and Ethiopia. About Bitdeer AI Lab : Bitdeer AI Lab is a frontier AI lab under Bitdeer, a global-leading computing power solutions provider. Guided by long-termism, we are committed to exploring the frontiers of artificial intelligence with the ambition, courage, and determination to build technologies that can truly change the world. Our mission is to turn energy into intelligence that people can actually afford to use. Inference is where that happens: every product built on a model is bounded by what it costs to run, so the economics of serving decide what gets built at all. We work on this from the ground up, from the power and datacenters we own to the software that turns them into tokens — and we continue to invest in and expand the infrastructure behind it. What you will be responsible for: This role exists to make our own research fast. Our efficiency work produces methods — new quantization schemes, sparsity patterns, attention variants, speculative decoding strategies — that have no efficient implementation available anywhere, because they did not exist before. You will write the kernels that turn those methods into real speedups on real hardware, and find the performance headroom that generic open-source implementations leave on the table for our specific models and traffic patterns. Concretely: writing and optimizing CUDA / Triton kernels for methods the team develops; performance attribution across our serving path, including roofline analysis and identifying which kernels dominate under our traffic mix; taking published methods whose reference implementations are too slow to be useful and making them production-viable; and building the measurement basis the rest of the team relies on. Your work is driven by the Lab's research agenda, in close collaboration with the AI Cloud platform team who own the serving stack itself. How you will stand out: Bachelor's, Master's, or PhD in Computer Science, Electrical Engineering, or a related field, with hands-on experience in GPU programming, high-performance computing, or ML systems Proficiency in CUDA and/or Triton, with concrete examples of kernels you have written or meaningfully optimized; strong Python and C++ Working knowledge of GPU architecture and memory hierarchy — occupancy, memory coalescing, tensor cores, warp-level primitives — with the profiling habits to back it up (Nsight Compute / Systems or equivalent) Hands-on experience optimizing inference-critical paths such as attention, GEMM, normalization, sampling, or KV-cache management Comfortable implementing methods that have no reference implementation available — working from a paper, a colleague's notebook, or a whiteboard sketch Ability to define your own measurement before optimizing, and to state honestly what a number does and does not prove Experience with inference engines such as vLLM, SGLang, or TensorRT-LLM, including writing custom kernels or extensions for them, is highly preferred Compiler or IR-level experience (MLIR, TVM, TorchInductor), or experience with distributed serving (tensor / pipeline parallelism), is highly preferred Publications at top-tier systems venues, or substantial open-source contributions to inference or GPU computing projects are welcome Deep enthusiasm for cutting-edge AI infrastructure and squeezing real performance out of hardware, with a strong ownership mentality and solid engineering discipline What you will experience working with us: A culture that values authenticity and diversity of thoughts and backgrounds; An inclusive and respectable environment with open workspaces and exciting start-up spirit; Fast-growing company with the chance to network with industrial pioneers and enthusiasts; Ability to contribute directly and make an impact on the future of the digital asset industry; Involvement in new projects, developing processes/systems; Personal accountability, autonomy, fast growth, and learning opportunities; Attractive welfare benefits and developmental opportunities such as training and mentoring.