Senior ML Engineer

Senior Machine Learning Engineer (Computer Vision – Object Detection)

Job Summary

We are looking for a hands-on Senior ML Engineer (Computer Vision) with deep expertise in object detection and strong production delivery skills.

You will own end-to-end detection systems — from dataset design and training pipelines to optimized inference services, monitoring, and continuous improvement in real-world environments.

Key Responsibilities

• Design, train, debug, and improve state-of-the-art object detection models
• Build robust training pipelines (datasets, augmentation, caching, versioning, reproducible experiments)
• Conduct systematic error analysis and ablation studies
• Develop advanced detection workflows (multi-stage pipelines, ensembles, custom post-processing)
• Optimize inference for GPU performance (latency, throughput, memory)
• Export and deploy models (ONNX, TorchScript, TensorRT)
• Build production services using Docker, Linux, CI/CD, FastAPI and/or gRPC
• Implement comprehensive testing (unit, integration, regression, golden test sets)
• Set up monitoring systems (logging, metrics dashboards, drift tracking, retraining triggers)
• Translate research papers into working prototypes and production systems

Required Skills & ExperiencePython & ML Engineering

• Advanced Python engineering (clean architecture, typing, testing, profiling)
• Strong hands-on experience with PyTorch (mandatory)
• TensorFlow (optional)
• Experiment tracking (W&B, MLflow)
• Config management (Hydra/OmegaConf)
• Dataset versioning (DVC or similar)

Computer Vision Fundamentals

• Strong CV foundations (geometry, distortions, preprocessing, camera models)
• OpenCV expertise
• Evaluation metrics: mAP, IoU, precision/recall, PR curves

Deep Object Detection

Experience with modern detectors such as:

• YOLO (v5/v8/v9)
• Faster R-CNN
• RetinaNet
• EfficientDet
• DETR variants

Experience with:

• Multi-stage detection pipelines
• Ensemble strategies
• Domain-optimized post-processing

Production ML & MLOps

• ONNX runtime + TorchScript or TensorRT
• GPU optimization & inference tuning
• Docker, Linux, CI/CD (GitHub Actions or GitLab CI)
• FastAPI and/or gRPC deployment
• Monitoring, model versioning, rollback strategies

Job Type: Fulltime - Onsite
Location: Lahore

Job Type: Full-time

Work Location: In person