AI / Embedded ML Engineer

E-Space is a company focused on making connectivity from space universally accessible and secure. The AI / Embedded ML Engineer will be responsible for the full lifecycle of AI/machine learning on resource-constrained hardware, including data ingestion, model development, optimization, and deployment on embedded devices.

Responsibilities:

• Design and build data ingestion pipelines from sensors including IMUs, accelerometers, gyroscopes, microphones, and other environmental sensors
• Handle raw sensor data: cleaning, labeling, synchronization, and storage
• Build tools to collect, version, and manage training datasets at scale
• Develop and train ML models for classification, regression, anomaly detection, and signal processing tasks
• Select appropriate model architectures for each problem and hardware target
• Fine-tune pre-trained models for domain-specific tasks and data distributions
• Design and run experiments to evaluate and compare model performance
• Optimize models for deployment on microcontrollers and edge processors such as ARM Cortex-M, RISC-V, and DSPs
• Apply quantization, pruning, and knowledge distillation to reduce model size and inference latency
• Use frameworks including TensorFlow Lite Micro, Edge Impulse, ONNX Runtime, and ExecuTorch
• Integrate ML inference into embedded firmware written in C, C++, or Rust
• Profile and optimize memory usage, power consumption, and real-time performance
• Design hybrid architectures that combine on-device lightweight models with LLM-based reasoning
• Build pipelines that route tasks between edge inference and cloud or edge-hosted LLM components
• Evaluate trade-offs in latency, accuracy, and power between on-device and LLM-assisted approaches
• Write clean, well-tested embedded software that integrates ML inference into real-time systems
• Work with RTOS environments such as FreeRTOS and Zephyr, as well as bare-metal firmware
• Collaborate with hardware and firmware teams to co-optimize the full system stack
• Document design decisions, pipeline configurations, model benchmarks, and deployment procedures
• Prepare technical reports and presentations for internal teams and stakeholders
• Stay current with developments in TinyML, embedded AI, and edge computing and bring relevant innovations into the team
• Work closely with cross-functional teams including hardware engineers, firmware developers, and data scientists
• Provide technical support during hardware bring-up, system integration, and field testing
• Participate in design reviews and contribute constructive feedback across the stack