remote
Application Software Engineer, Inference - SpaceX
Software Engineer
Application Software Engineer, Inference building mission‑critical inference pipelines using Python, C++, and ML frameworks on AWS, containerized with Docker to support SpaceX launch and Starlink operations.
About the role
Key Responsibilities
- Design, develop, and maintain high‑performance inference services that process telemetry and sensor data for launch vehicle and Starlink systems.
- Implement scalable, containerized solutions on AWS, ensuring reliability, low latency, and fault tolerance.
- Collaborate with cross‑functional teams to integrate ML models, optimize inference pipelines, and monitor performance metrics.
- Write clean, well‑documented code in Python and C++, following best practices and rigorous testing.
- Participate in code reviews, continuous integration, and deployment workflows to deliver production‑ready software.
Requirements
- 3+ years of software engineering experience in a high‑stakes environment.
- Proficiency in Python and C++ with a strong understanding of concurrency and performance tuning.
- Hands‑on experience with ML inference frameworks (TensorFlow, PyTorch) and model deployment.
- Solid knowledge of AWS services (EC2, ECS, EKS, S3, Lambda) and container orchestration with Docker.
- Excellent problem‑solving skills, strong communication, and a collaborative mindset.
Skills
pythoncmachine learningawsdocker