Edge AI Engineer: Deploy Production Models

Tradermath; Bellevue (WA); Hybrid; USD 155,000 - 193,000; Full time

Benefits offered by this job

Medical, dental, and vision (subsidizd

401(k)

Unlimited PTO

HSA/FSA

14 paid company holidays

Job summary

Armada seeks exceptional AI Engineers to build and deploy intelligent systems at the edge of the physical world. You will develop production AI for offshore platforms, remote mines, defense installations, transportation networks, industrial facilities, autonomous systems, and distributed camera and sensor networks.

These systems must perform under intermittent connectivity, latency, and security constraints.

Qualifications

• Master’s or PhD in applied mathematics, computer science, computational science, engineering, or a related technical field.
• 3+ years of industry experience in AI research, ML, and production software development.
• Strong programming in Python and proficiency in Java, C++, or another production language.
• Hands-on experience with statistical ML, deep learning, and NLP.
• Understanding of supervised, unsupervised, transfer, and representation learning.
• Experience with transformers, CNNs, detection models, generative models, and autoencoders.
• Proficiency with PyTorch, TensorFlow, or JAX.
• Familiarity with containers, numerical libraries, modular software design, version control, and automated testing.
• Experience deploying ML to real-world problems beyond research prototypes.
• Publications/open-source contributions or production systems are valued.

Responsibilities

• Translate operational problems into AI requirements, datasets, evaluation criteria, and production architectures.
• Design, train, fine-tune, and deploy models for vision, language, multimodal AI, time-series, autonomy, and optimization.
• Apply state-of-the-art research using fine-tuning, distillation, quantization, and hybrid AI approaches.
• Build training and evaluation datasets from video, images, text, telemetry, sensor data, and synthetic data.
• Evaluate models for accuracy, latency, throughput, robustness, safety, groundedness, and resource efficiency.
• Optimize inference through quantization, pruning, distillation, batching, caching, and hardware-aware acceleration.
• Build reliable AI services using Python, testing, versioning, observability, and automated deployment.
• Deploy containerized AI workloads across Kubernetes, cloud, on-premises, and disconnected edge environments.
• Build pipelines for model monitoring, data validation, drift detection, retraining, and controlled updates.
• Partner with customers, product teams, engineers, and domain experts to move prototypes into production.
• Diagnose issues across data pipelines, models, GPUs, orchestration, networking, and applications.
• Contribute reusable models, datasets, evaluation tools, platform components, documentation, patents, and publications.

Skills

Python

Java

C++

NLP

Deep learning

PyTorch

TensorFlow

JAX

Containers

ML deployment

Education

Master's or PhD in applied mathematics, computer science, computational science, engineering, or related field

Tools

PyTorch

TensorFlow

JAX

TensorRT

Triton Inference Server

ONNX Runtime

vLLM

CUDA

Kubernetes

Job description

Armada seeks exceptional AI Engineers to build and deploy intelligent systems at the edge of the physical world. You will develop production AI for offshore platforms, remote mines, defense installations, transportation networks, industrial facilities, autonomous systems, and distributed camera and sensor networks.

These systems must perform under intermittent connectivity, latency, and security constraints.