HPC Developer

Type: Full-Time

Comp: Open (in the truest sense of the word — the firm is looking for Subject Matter Experts)

Location: Philadelphia Metro Area

Relocation & Visa: Visa transfer available for the right candidate. Very generous relocation package provided.

Company: A Leading Quantitative Research & Technology Firm — The Perfect Mix of Google Meets Science Meets Finance

Important for the Role

This is not a typical HPC development job — it’s an opportunity to engineer the backbone of one of the most data-intensive, performance-sensitive environments in the private sector.

Ideal candidates will demonstrate:

· Deep performance tuning intuition — from hardware-aware code to system-wide optimizations.

· Ownership mentality — if something’s broken or missing, you fix it or build it, fast.

· Strong data analysis instincts — you don’t just write code, you dig into results and understand where and why things fall short.

· Monitoring obsession — when 100 machines run a simulation and 99 idle, you’re already debugging.

· Simulation experience — you’ve written and optimized software that mimics scientific, engineering, or market systems at scale.

· Load balancing fluency — you understand how to effectively distribute work across diverse architectures and workloads.

· GPU mapping expertise — you know how to convert complex math or science code into highly parallelized GPU kernels.

About the Firm

We are a globally recognized, technology-first research organization operating at the intersection of high-performance computing, machine learning, and scientific inquiry. Our infrastructure supports a growing base of elite researchers who rely on enormous volumes of data, heterogeneous compute clusters, and custom accelerators to build new insights and capabilities.

We’re scaling fast — more data, more models, more demanding workloads — and we need great engineers to help us scale the software, too.

About the Role

This is a development-heavy role focused on creating tools, libraries, and frameworks that drive research productivity and computational performance. You’ll work directly with researchers, infrastructure engineers, and systems architects to create a high-performance, user-friendly environment for data exploration, simulation, feature generation, and model development.

This is a full-time, onsite role at our Philadelphia-area office. Visa transfers and relocation packages are available.

Key Focus Areas

· High-Performance Tooling: Build performant, usable tools and libraries that enable researchers to work productively with massive data and demanding algorithms.

· Simulation & Modeling: Develop and tune simulation frameworks that execute across varied hardware—from CPUs to GPUs to FPGAs.

· Load Balancing & Scalability: Design systems that distribute work efficiently and maximize hardware utilization under diverse loads.

· Advanced Monitoring & Diagnostics: Build observability into every layer—spot underutilization, identify latency sources, and guide optimization with data.

· Cross-Platform Optimization: Map scientific, mathematical, or ML models to the most appropriate compute backend—whether it’s a CPU, GPU, or a custom accelerator.

Responsibilities

· Develop and maintain scalable, high-performance software components and toolkits.

· Collaborate closely with researchers to build features that streamline workflows and enhance reproducibility.

· Write simulation software that accurately models physical, engineering, or financial systems and runs efficiently at scale.

· Profile and optimize code across architectures (e.g., CPU, GPU, FPGA).

· Implement monitoring tools to track resource usage and identify computation bottlenecks before they affect users.

· Translate complex computation and data processing tasks into parallelized workloads and pipelines.

· Ensure system balance across compute, storage, and network layers.

Must-Have:

· Proficiency in C/C++, Python, or similar system-level programming languages.

· Deep experience in HPC systems, simulation software, and performance engineering.

· Strong background in data analysis, profiling, and debugging at scale.

· Experience writing optimized code for multi-core CPUs, GPUs (CUDA/OpenCL), or FPGAs.

· Familiarity with profiling tools such as perf, Nsight, VTune, or similar.

· Demonstrated ability to analyze workload distribution, tune load balancing, and increase computational throughput.

· Background working in large-scale, high-throughput environments.

· Exposure to machine learning workflows (training, inference, feature pipelines).

· Experience with FPGA toolchains and high-level synthesis.

· Familiarity with containerized HPC environments (Apptainer/Singularity, Docker).

· Experience using HPC schedulers such as Slurm in multi-user, high-demand settings.

What We Offer

· A rare opportunity to work on massive-scale infrastructure with a mandate to innovate, not maintain.

· Deeply technical, high-performing teammates who value precision, impact, and curiosity.

· Competitive compensation including:

o Full-time employment with elite compensation packages

o Visa sponsorship and transfer support

o Substantial relocation support for both domestic and international hires