Senior HPC Software Engineer - In-Space Payload Runtime

Blue Origin; Littleton (CO); On-site; USD 182,000 - 254,000; Full time

Benefits offered by this job

Medical insurance

Dental and Vision insurance

Paid parental leave

Disability coverage

401(k) with company match

Education support

Job summary

Blue Origin seeks an experienced software engineer to own the payload processing runtime, driving stateful, fault-tolerant in-space compute for diverse workloads. You will integrate accelerator frameworks, optimize performance on orbital hardware, and define robust job submission APIs with clear latency expectations.

You will also design checkpointing, benchmark performance, and collaborate with orchestration teams to ensure resilient, scalable system behavior across intermittent satellite

Qualifications

• BSCS or similar required; strong background in HPC and distributed systems.
• Experience deploying data-intensive apps on large-scale accelerated computing systems.
• Strong understanding of accelerator architecture (GPUs) and memory bandwidth.

Responsibilities

• Own the on-board payload processing runtime architecture and implementation.
• Integrate and optimize accelerator compute frameworks and workloads for orbital hardware.
• Design robust checkpointing and state persistence for intermittent connectivity.
• Define API contracts for job submission and results with latency SLAs and error handling.
• Develop performance benchmarks to profile throughput, latency, and power.

Skills

HPC

Distributed systems

GPU acceleration

Fault tolerance

State management

Education

BSc in Computer Science/Engineering

Master’s or PhD (preferred)

Tools

Containerization (Docker)

Orchestration (Kubernetes)

Job description

Blue Origin seeks an experienced software engineer to own the payload processing runtime, driving stateful, fault-tolerant in-space compute for diverse workloads. You will integrate accelerator frameworks, optimize performance on orbital hardware, and define robust job submission APIs with clear latency expectations.

You will also design checkpointing, benchmark performance, and collaborate with orchestration teams to ensure resilient, scalable system behavior across intermittent satellite