PhD in HPC | Ex-Fintech Engineer | Expert in C++/Python & GPU Programming | Passionate about performance, simulation & code that runs fast | Badminton Enthusiast.
I thrive on pushing the limits of what is possible on modern CPUs and GPUs. As a PhD researcher in High-Performance Computing with over eight years of experience in C++ and Python, I specialize in building high-throughput, performance-critical systems. My work spans low-latency trading pipelines and massively parallel scientific simulations.
I have contributed to core backend systems for global stock exchanges and developed a C++ domain-specific language that accelerates nuclear fusion simulations across thousands of CPUs and GPUs. My technical toolkit includes MPI, OpenMP, CUDA, HIP, and SYCL. I am also skilled in distributed computing, performance profiling, source-to-source code transformation, and optimization on Linux systems.
I am passionate about solving complex engineering problems, where software performance and scalability matter most. I enjoy working on systems that combine deep technical challenges with real-world impact, particularly in simulation technologies and financial infrastructure.
- Heterogeneous Computing and Portable Parallel Programming.
- Domain-Specific Simulation Frameworks and Source-to-Source Translation.
- CPU/GPU Programming & Optimization.
- Particle-in-Cell (PIC) simulations and Numerical Solvers in Simulation Pipelines.
- Performance benchmarking and Analysis.
- Specialist Software Engineer β 4.5+ years designing and developing low-latency software solutions for fintech applications.
- IT Research Assistant β 6 months conducting research on human group detection through video processing.
- PhD in Computer Science (High-Performance Computing), University of Warwick, United Kingdom (July 2025).
- BSc Engineering (Hons) in Electronic and Telecommunication, University of Moratuwa, Sri Lanka.
- Advanced Level (Mathematics Stream), Isipathana College, Colombo, Sri Lanka.
- IBM AI Engineering Professional Certificate β Coursera (in progress)
- Machine Learning Specialization β DeepLearning.AI, Stanford and Coursera (Certificate)
- Fundamentals of Accelerated Computing with CUDA Python β NVidia (Certificate)
π¨βπ» Programming Languages:
C/C++, Python, Java, Scala, C#
βοΈ Parallel Programming & HPC:
Threads, OpenMP, MPI, CUDA, HIP, SYCL, Kokkos, Legion
π₯οΈ Hardware:
CPUs: Intel, AMD || GPUs: NVIDIA, AMD, Intel
Tested on: LUMI-G, ARCHER2, DiRAC-Tursa, Sulis, Bede β’ Avon
π Profiling & Debugging:
Intel VTune, Intel Advisor, Valgrind, GDB, Arm Forge DDT, Nsight Compute/ nvProf, ROCm Profiler
π§ͺ Build & CI/CD Tools:
CMake, Make, Jenkins, Bamboo, Git, Spack, Docker, SLURM
π Testing & QA:
GTest, JUnit, JBehave
ποΈ Databases & Documentation:
Oracle, PostgreSQL, Confluence, JIRA
π Data & Analysis:
MATLAB, Pandas, NumPy, Matplotlib
- π§ zaman.lantra@gmail.com | zaman.lantra@warwick.ac.uk
- πΌ LinkedIn
- π§βπ» University Profile
