About The Position
This role is part of Blue Origin’s Advanced Concepts and Enterprise Engineering (ACE) organization and supports Project Sunrise, a constellation of orbital data centers. The Application Software Engineer will focus on Machine Learning Systems, ensuring customer AI models run efficiently on the orbital platform. The role centers on inference optimization: adapting and compiling complex neural networks to achieve high performance within space-related power, thermal, and compute constraints. It combines low-level AI model performance engineering with aerospace applications. The role involves profiling and optimizing deep learning models, building tools and pipelines for customer model onboarding, and collaborating with customers and internal compute platform and flight software teams. Travel may be required up to 10% of the time. Relocation assistance is available.
Requirements
- Bachelor's degree in Computer Science, Electrical Engineering, or a related technical field.
- At least 3 years of professional software engineering experience.
- Strong programming skills in Python and/or C++.
- Demonstrated experience with at least one major deep learning framework, such as PyTorch, TensorFlow, or JAX.
- Solid understanding of deep learning concepts and modern neural-network architectures.
- Must be a U.S. citizen or national, U.S. permanent resident (current Green Card holder), or lawfully admitted into the U.S. as a refugee or granted asylum.
Nice To Haves
- Master's degree or PhD in a relevant field.
- Direct experience with model optimization, quantization, and/or compilation for hardware accelerators such as GPUs or TPUs.
- Familiarity with NVIDIA tools such as TensorRT and Triton Inference Server.
- Experience profiling and analyzing low-level code.
- Passion for maximizing hardware performance.
- Knowledge of computer architecture.
Responsibilities
- Analyze and profile deep learning models to identify performance bottlenecks on on-orbit compute hardware.
- Use model optimization and compilation frameworks, such as ONNX, TensorRT, and TVM, to accelerate inference.
- Develop quantization, pruning, and other optimization techniques for power- and thermally-constrained environments.
- Create and maintain a software toolkit and pipeline for onboarding and optimizing customer AI models.
- Collaborate with customers to understand their models and help them achieve performance targets on the platform.
- Work with compute platform and flight software teams to understand hardware capabilities and constraints.
- Keep current with research and industry best practices in efficient deep learning and model optimization.
Benefits
- Medical, dental, and vision insurance.
- Basic and supplemental life insurance.
- Paid parental leave.
- Short- and long-term disability insurance.
- 401(k) with company match of up to 5%.
- Education Support Program.
- Stock options for regular employees working at least 20 hours per week.
- Up to four weeks of paid time off per year based on weekly scheduled hours.
- Up to 14 company-paid holidays.
- Depending on role type and job level, potential benefits and bonuses based on company policy and discretion.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Mid Level
