Lead Edge AI/ML Engineer

Arcfield; Home Creek (VA); On-site; USD 101,657 - 200,020; Full time

Job summary

Arcfield’s Strategic Technology Consulting (STC) seeks a Lead Edge AI/ML Engineer to design, optimize, and deploy advanced AI/ML for swaP-constrained tactical edge systems in contested environments.

The role emphasizes real-time embedded deployment, model optimization (quantisation, pruning), C++ inference engines, and collaboration with PNT, embedded software, hardware integration, and systems engineering to deliver deployable AI capabilities with minimal human intervention.

Qualifications

• Production deployment of ML models in edge/embedded environments.
• Experience with quantisation, pruning, distillation for edge constraints.
• U.S. DoD Secret Security Clearance eligibility/obtainable.

Responsibilities

• Architect end-to-end Edge AI pipelines from data to deployment on low-Swap edge accelerators (GPUs, NPUs, FPGAs).
• Design autonomous watchdog agent for fault prediction and prompt repair.
• Integrate ML into state-estimation with NAVWAR spoofing defense and sensor fusion.
• Translate PyTorch/TensorFlow models into optimized C++ inference engines using TensorRT/ONNX/edge SDKs.
• Optimise for SwaP with quantisation and pruning.
• Define ML architecture, mentor juniors, and present to stakeholders.

Skills

Python

C++

Edge AI

ML deployment

Team leadership

CI/CD / MLOps

Education

BS/MS/PhD in Computer Science, Machine Learning, Robotics, Electrical Engineering, or related field

Tools

TensorRT

ONNX Runtime

TFLite

OpenVINO

NVIDIA Jetson

FPGA/SoC platforms

Job description

Responsibilities

Strategic Technology Consulting (STC), an Arcfield Company, is seeking a Lead Edge AI / Machine Learning Engineer to lead the design, optimisation, and deployment of advanced AI/ML capabilities for swaP‑constrained tactical edge systems operating in contested environments. This role will lead the development of onboard AI/ML capabilities that improve resilient PNT performance through RF signal classification, IMU drift modelling, anomaly detection, and advanced sensor fusion. The engineer will also develop autonomous monitoring capabilities that track system health, thermal conditions, data integrity, sensor status, and software performance, enabling the system to detect issues, diagnose problems, and take corrective action when failures occur. The ideal candidate will bring deep experience moving AI/ML beyond prototype environments into real‑time embedded systems, with expertise in model optimisation techniques such as quantisation, pruning, and efficient inference, as well as the ability to deploy production‑quality models into C++‑based embedded architectures. This role requires close collaboration with PNT, embedded software, hardware integration, and systems engineering teams to deliver deployable AI‑enabled capabilities that preserve mission continuity without relying on continuous human intervention.

• Architect Edge AI Pipelines: Lead the end‑to‑end development of machine learning pipelines, from data curation and model training to final deployment on low‑Swap edge inference accelerators (GPUs, NPUs, FPGAs).
• Build the Agentic Watchdog: Design and deploy a highly autonomous reinforcement learning or anomaly‑detection agent to predict, detect, and instantly clear hardware or software faults.
• Enhance AI Navigation Fusion: Collaborate directly with PNT engineers to integrate ML into the state‑estimation loop, using neural networks to classify NAVWAR spoofing attacks, model complex inertial sensor noise, or fuse intermittent visual/RF data.
• Bridge the AI/Embedded Gap: Partner with embedded C++ and DSP engineers to translate heavy PyTorch/TensorFlow models into highly optimised, deterministic C++ inference engines using TensorRT, ONNX Runtime, or edge‑specific SDKs.
• Optimise for SwaP: Execute extreme model quantisation (INT8, FP16), pruning, and knowledge distillation to ensure AI models don’t exceed strict memory, thermal, and compute‑latency budgets.
• Lead the Technical Vision: Define the ML architecture for the programme, manage junior engineers/data scientists, and interface directly with end‑customers/stakeholders during capability demonstrations.

Qualifications

• BS 8‑10, MS 6‑8, PhD 3‑5 (degree in Computer Science, Machine Learning, Robotics, Electrical Engineering, or a related technical field).
• Experience developing and deploying machine learning models to production environments, with a strong focus on Edge AI or embedded systems.
• Fluency in Python (for training/architecture) and modern C++ (for edge deployment and embedded integration).
• Deep expertise with ML optimisation frameworks and runtimes (e.g. TensorRT, ONNX, TFLite, OpenVINO) targeting edge hardware (like NVIDIA Jetson, Coral, or Xilinx SoCs).
• Demonstrated experience developing autonomous agents, anomaly‑detection algorithms, or reinforcement learning systems applied to complex hardware/software ecosystems.
• Proven ability to collaborate intimately with embedded software, DSP, or systems engineers to deploy AI into real‑time, deterministic systems.
• Familiarity with hardware‑in‑the‑loop (HITL) testing and CI/CD pipelines for machine learning models (MLOps).
• Must be able to obtain and maintain a U.S. DoD Secret Security Clearance.

Compensation

Projected compensation range for this position: Min $101,657.48 – Max $200,020.88.

EEO Statement

We are an equal‑opportunity employer and federal government contractor. We do not discriminate against any employee or applicant for employment as protected by law.