Machine Learning Engineer at SAIC

Ashburn, Virginia, United States -

Full Time

Start Date

Immediate

Expiry Date

24 Feb, 26

Salary

0.0

Posted On

26 Nov, 25

Experience

5 year(s) or above

Remote Job

Yes

Telecommute

Yes

Sponsor Visa

Skills

Machine Learning, Computer Vision, Biometrics, Image Processing, Deep Learning, Object Detection, OCR, Face Recognition, GCP, Vertex AI, MLOps, Python, TensorFlow, PyTorch, Docker, Data Engineering

Industry

Defense and Space Manufacturing

Description

SAIC is seeking an experienced Machine Learning Engineer with strong expertise in computer vision, biometrics, and image processing to support the development and deployment of advanced AI/ML capabilities across our surveillance and sensor-integration platforms. This role focuses on designing, optimizing, and operationalizing ML models that run on both edge GPU systems and our cloud training environment The ideal candidate has applied ML experience, including camera-based detection/classification, LPR/OCR, and biometric analytics. Experience with Google Cloud Platform (GCP), Vertex AI, and MLOps pipelines is highly desirable. Key Responsibilities Computer Vision & Biometrics Model Development Develop, train, and optimize deep learning models for object detection, tracking, classification, OCR/LPR, face recognition, and other biometric modalities. Improve robustness under challenging conditions (low light, IR, glare, long-range imaging, motion blur, environmental effects). Implement preprocessing algorithms: normalization, data augmentation, background suppression, video frame sampling, image enhancement. Edge AI Inference & Optimization Deploy ML models onto GPU-accelerated edge compute devices (NVIDIA RTX, rugged edge systems). Optimize models with TensorRT, ONNX Runtime, and performance tuning (FP32/FP16/INT8, pruning, quantization). Design inference pipelines with batching, backpressure management, and latency optimization for real-time workloads. Cloud Integration & MLOps (Highly Desirable) Collaborate with data engineering and cloud teams on: Training pipelines Data ingestion and labeling flows Model evaluation, versioning, and promotion Work with GCP services including: Vertex AI Pipelines Vertex AI Training / Endpoints Cloud Storage (GCS) BigQuery (optional) Contribute to end-to-end MLOps workflows (CI/CD for ML, artifact tracking, automated deployments). Data Engineering & Sensor Fusion Build datasets from EO/IR cameras, LPR/QR/RFID sources, and radar-aligned video streams. Implement multi-modal correlation logic (video, metadata, sensor outputs). Perform error analysis and iterative retraining to improve performance across field conditions. Testing & Field Validation Support lab and field testing of models in real operational environments. Evaluate accuracy, false positives/negatives, latency, throughput, and precision/recall. Document findings, propose improvements, and ensure model readiness for deployment. Collaboration & Documentation Work with architects, software and hardware engineers, and solution delivery teams to deliver a scalable, maintainable ML architecture. Participate in design reviews, code reviews, and technical deep dives. Produce clear technical documentation for model behavior, assumptions, data constraints, and limitations. Required Qualifications Bachelor’s in Computer Science, Electrical Engineering, Machine Learning, or related discipline and 5 years of experience designing and implementing machine learning models. Additional years of experience may be considered in lieu of a degree. Strong hands-on experience in: PyTorch or TensorFlow Computer vision algorithms and data augmentation Object detection (YOLO, SSD, Faster R-CNN, etc.) OCR/LPR workflows Face detection/recognition or other biometrics Practical experience deploying and optimizing models for real-time GPU inference. Strong Python skills; familiarity with C++ is a plus. Experience with Docker containers and modern development workflows. Preferred / Highly Desirable Qualifications Experience with GCP, specifically: Vertex AI Training Vertex AI Pipelines Vertex AI Model Registry / Endpoints Experience building or integrating into MLOps pipelines (CI/CD, automated training, model versioning, monitoring). Background with multi-sensor systems (EO/IR video, radar, RFID, OCR/LPR integration). Experience optimizing ML for resource-constrained edge environments. Familiarity with Kafka or distributed streaming architectures. Experience working on government, defense, or mission-critical systems. Strong analytical thinking and focus on scientific rigor. Ability to work independently while collaborating across cross-functional teams. Excellent communication skills for complex technical subjects. A mindset oriented toward continuous improvement and real-world impact.

Responsibilities

The Machine Learning Engineer will develop, train, and optimize deep learning models for various applications including object detection and biometric analytics. The role also involves deploying models on edge devices and collaborating with cloud teams for MLOps workflows.