CUDA Kernel Optimizer
vor 2 Wochen
1) Role Overview
Mercor is engaging advanced CUDA experts who specialize in GPU kernel optimization, performance profiling, and numerical efficiency. These professionals possess a deep mental model of how modern GPU architectures execute deep learning workloads. They are comfortable translating algorithmic concepts into finely tuned kernels that maximize throughput while maintaining correctness and reproducibility,
2) Key Responsibilities
-
Develop, tune, and benchmark CUDA kernels for tensor and operator workloads.
-
Optimize for occupancy, memory coalescing, instruction-level parallelism, and warp scheduling.
-
Profile and diagnose performance bottlenecks using Nsight Systems, Nsight Compute, and comparable tools.
-
Report performance metrics, analyze speedups, and propose architectural improvements.
-
Collaborate asynchronously with PyTorch Operator Specialists to integrate kernels into production frameworks.
-
Produce well-documented, reproducible benchmarks and performance write-ups.
3) Ideal Qualifications
-
Deep expertise in CUDA programming, GPU architecture, and memory optimization.
-
Proven ability to achieve quantifiable performance improvements across hardware generations.
-
Proficiency with mixed precision, Tensor Core usage, and low-level numerical stability considerations.
-
Familiarity with frameworks like PyTorch, TensorFlow, or Triton (not required but beneficial).
-
Strong communication skills and independent problem-solving ability.
-
Demonstrated open-source, research, or performance benchmarking contributions.
4) More About the Opportunity
-
Ideal for independent contractors who thrive in performance-critical, systems-level work.
-
Engagements focus on measurable, high-impact kernel optimizations and scalability studies.
-
Work is fully remote and asynchronous; deliverables are outcome-driven.
-
Access to shared benchmarking infrastructure and reproducibility tooling via Mercor support resources.
5) Compensation & Contract Terms
-
Typical range: $120–$250/hour, depending on scope, specialization, and results achieved. Payments will be based on accepted task output over flat hourly.
-
Structured as a contract-based engagement, not an employment relationship.
-
Compensation tied to measurable deliverables or agreed milestones.
-
Confidentiality, IP, and NDA terms as defined per engagement.
6) Application Process
-
Submit a brief overview of prior CUDA optimization experience, profiling results, or performance reports.
-
Include links to relevant GitHub repos, papers, or benchmarks if available.
-
Indicate your hourly rate, time availability, and preferred engagement length.
-
Selected experts may complete a small, paid pilot kernel optimization project
7) About Mercor
-
Mercor connects domain experts with top AI research and technology organizations through project-based contracts.
-
Contractors operate independently, with full flexibility over methods, timelines, and tools.
-
Our mission is to help top engineers and researchers access frontier technical work without rigid employment structures.
-
PyTorch Operator
vor 2 Wochen
Berlin, Berlin, Deutschland Mercor Vollzeit 120.000 $ - 240.000 $ pro Jahr1) Role Overview Mercor is seeking experienced PyTorch experts who excel in extending and customizing the framework at the operator level. Ideal contributors are those who deeply understand PyTorch's dispatch system, ATen, autograd mechanics, and C++ extension interfaces. These contractors bridge research concepts and high-performance implementation,...
-
Senior ML Scientist, GenAI
Vor 5 Tagen
Berlin, Berlin, Deutschland Picsart Vollzeit 120.000 € - 180.000 € pro JahrAt Picsart, we bring the wonder of creativity to the world and make it easy. As a Senior ML Scientist on our Generative Computer Vision team, you'll help invent and deploy breakthrough generative AI capabilities for millions of creators globally. Your work will shape the future of visual expression by building state-of-the-art tools at the intersection of...
-
Embedded Linux Software Engineer
vor 2 Wochen
Berlin, Berlin, Deutschland EnduroSat Vollzeit 60.000 € - 120.000 € pro JahrAbout usWe are EnduroSat A fast-growing space scale-up at the forefront of satellite innovation, specializing in advanced software-flexible satellites for commercial, governmental, and scientific endeavors.This is more than a job, it`s a missionWe are making space universally accessible and redefining the possibleWe get things doneWe take ownership of what...
-
Software Engineer
Vor 6 Tagen
Berlin, Berlin, Deutschland Sonova AG Vollzeit 60.000 € - 120.000 € pro JahrJob descriptionYou will be part of Audatic's development team. Every member of the development team is encouraged to take ownership and responsibility for part of our DNN training infrastructure. We work on a variety of challenges surrounding deep learning, so there will be opportunities for you to work on various topics and learn new skills or expand...
-
Senior ML Scientist, GenAI
Vor 6 Tagen
Berlin, Berlin, Deutschland Picsart Vollzeit 120.000 € - 240.000 € pro JahrAt Picsart, we bring the wonder of creativity to the world and make it easy. As a Senior ML Scientist on our Generative Computer Vision team, you'll help invent and deploy breakthrough generative AI capabilities for millions of creators globally. Your work will shape the future of visual expression by building state-of-the-art tools at the intersection of...
-
Senior Software Engineer
Vor 7 Tagen
Berlin, Berlin, Deutschland Sonova Group Vollzeit 90.000 € - 120.000 € pro JahrJob DescriptionYou will be part of Audatic's development team. Every member of the development team is encouraged to take ownership and responsibility for part of our DNN training infrastructure. We work on a variety of challenges surrounding deep learning, so there will be opportunities for you to work on various topics and learn new skills or expand...
-
Software Engineer
Vor 7 Tagen
Berlin, Berlin, Deutschland Sonova Group Vollzeit 75.000 € - 90.000 € pro JahrMore About The RoleYou will be part of Audatic's development team. As such, you'll be encouraged to take ownership and responsibility for part of our DNN training infrastructure. Below is a list of the dev team's responsibilities. Together, we'll choose a few for you to focus on and these can evolve over time.Working very closely with our deep learning...
-
Software Platform Engineering Manager
Vor 5 Tagen
Berlin, Berlin, Deutschland Canonical - Jobs Vollzeit 100.000 € - 200.000 € pro JahrCanonical is a leading provider of open source software and operating systems to the global enterprise and technology markets. Our platform, Ubuntu, is very widely used in breakthrough enterprise initiatives such as public cloud, data science, AI, engineering innovation, and IoT. Our customers include the world's leading public cloud and silicon providers,...
-
Senior Software Engineer
Vor 5 Tagen
Berlin, Berlin, Deutschland Sonova Vollzeit 60.000 € - 120.000 € pro JahrWho we areAt Audatic, we build systems to render speech from any sound scenario clear and free of noise using state-of-the-art deep learning technology. Our mission is to empower millions of people with hearing loss to enjoy interactions in demanding social settings like bars or restaurants.As a part of the Sonova Group, our team developed the speech...
-
Embedded Linux Senior Software Engineer
Vor 5 Tagen
Berlin, Berlin, Deutschland Canonical - Jobs Vollzeit 80.000 € - 120.000 € pro JahrWork across the full Linux stack from kernel through GUI to optimise Ubuntu, the world's most widely used Linux desktop and server, for the latest silicon.The role is a fast-paced, problem-solving role that's challenging yet very exciting. The right candidate must be resourceful, articulate, and able to deliver on a wide variety of solutions across PC and...