Job Title

Compiler LeadHyderabadFounded by highly respected Silicon Valley veterans - with its design centers established in Santa Clara, California. / Hyderabad/Bangalore A US based well-funded product-based startup looking for Highly talented Verification Engineers for the following roles.We are looking for a highly experienced systems engineer with deep expertise in compilers, machine learning infrastructure, and system-level performance optimization. This role is hands-on and research-driven, ideal for someone who thrives on solving low-level performance challenges and building core infrastructure that powers next-generation AI workloads.Key Responsibilities:Compiler Design & OptimizationDevelop and enhance compiler toolchains based on LLVM, MLIR, Open64, or Glow.Build and optimize intermediate representations, custom dialects, and code generation flows for AI accelerators.Implement transformations and optimizations for latency, memory usage, and compute efficiency.AI System IntegrationWork closely with hardware teams to co-design compilers targeting custom silicon.Integrate compiler backends with ML frameworks like PyTorch, TensorFlow, or ONNX.Build graph-level and kernel-level transformations for AI training and inference pipelines.Performance Tuning & System AnalysisConduct low-level profiling and performance tuning across compiler and runtime layers.Identify and eliminate bottlenecks across CPU/GPU/NPU workloads.Develop parallel programming solutions leveraging SIMD, multi-threading, and heterogeneous computing.Tooling & InfrastructureDevelop tooling for performance analysis, debug, and test automation.Contribute to internal SDKs and devkits used by AI researchers and system engineers.Required Skills & Experience:Strong compiler development experience using LLVM, MLIR, Glow, or similar toolchains.Proficiency in C/C++, with solid command of Python for tooling and automation.In-depth understanding of compiler internals, including IR design, lowering, codegen, and scheduling.Deep knowledge of hardware-software co-design, particularly for AI/ML workloads.Experience with runtime systems, memory models, and performance modeling.Solid grasp of parallel and heterogeneous computing paradigms.Nice to Have:Experience working with custom AI hardware or edge inference platforms.Familiarity with quantization, scheduling for dataflow architectures, or compiler autotuning.Contributions to open-source compiler projects (e.g., LLVM, MLIR, TVM).Qualifications:Bachelor’s or Master’s degree in Computer Science, Electrical Engineering, or a related field.10–15 years of relevant hands-on experience in compilers, systems programming, or AI infrastructure.Contact:UdayMulya Technologiesmuday_bhaskar@"Mining The Knowledge Community"