Key Facts

Remote From:

Pakistan

Full time

Senior (5-10 years)

English

Hard Skills

Other Skills

•
Decision Making

Roles & Responsibilities

Advanced Python engineering: clean architecture, packaging, typing, testing, and profiling; strong PyTorch experience (required)
Deep object detection expertise with hands-on experience in detectors (e.g., YOLO v5/v8/v9, Faster R-CNN, RetinaNet, DETR); ability to build multi-stage detection workflows, ensembles, and specialized post-processing
Experiment tracking and reproducibility: experience with WB/MLflow, deterministic runs and seed control; config management using Hydra and/or OmegaConf; data pipelines with PyTorch Dataset/DataLoader, augmentation, caching, and dataset versioning (DVC or equivalent)
Production ML / MLOps capabilities: model export/serving (ONNX, TorchScript, or TensorRT), GPU optimization, deployment (Docker/Linux, CI/CD), and API services (FastAPI and/or gRPC)

Requirements:

Design, train, debug, and improve state-of-the-art object detection models for real-world conditions; optimize inference for latency, throughput, and memory
Build robust end-to-end training pipelines: datasets, augmentation, caching, versioning, and reproducible experiments; perform systematic error analysis and ablations to isolate failure modes
Deliver production-grade services using Docker, Linux, CI/CD, and APIs (FastAPI and/or gRPC); implement testing strategies across the pipeline (unit, integration, regression)
Set up monitoring and maintenance: logging, metrics dashboards, drift/performance tracking, retraining triggers; write clear technical documentation and translate research ideas into deployable components

Job description

Our client Big Entities is looking for Senior ML Engineer to work remotely.

Location: DHA Phase 3 (Remote)

Timings: 10 AM - 7 PM (Fri - Sat Off days)

Role Summary
We are looking for a hands-on Computer Vision and ML Engineer with deep expertise in deep object detection and strong production delivery skills. You will own end-to-end detection systems, from dataset and training pipelines to optimized inference services, monitoring, and continuous improvement.

Key Responsibilities

Design, train, debug, and improve state-of-the-art object detection models for real-world conditions
Build robust training pipelines: datasets, augmentation, caching, versioning, and reproducible experiments
Perform systematic error analysis and ablations to isolate failure modes (data vs model vs inference vs post-processing)
Develop custom detection systems beyond standard training, including multi-stage pipelines, ensembles, and specialized post-processing
Optimize inference for latency, throughput, and memory, including GPU acceleration and export toolchains
Deliver production-grade services using Docker, Linux, CI/CD, and APIs (FastAPI and/or gRPC)
Implement testing strategy across the pipeline (unit, integration, regression), including golden image test sets
Set up monitoring and maintenance: logging, metrics dashboards, drift/performance tracking, retraining triggers
Write clear technical documentation, architecture decisions, and trade-off analyses
Read research papers and rapidly translate ideas into working prototypes and deployable components

Required Skills and Experience:

Python and ML Engineering

Advanced Python engineering: clean architecture, packaging, typing, testing, profiling
Strong PyTorch experience (must)
TensorFlow optional
Strong model debugging skills and disciplined experimentation
Experiment tracking and reproducibility: W&B and/or MLflow, deterministic runs, seed control
Config management: Hydra and/or OmegaConf
Data pipelines: PyTorch Dataset/DataLoader, augmentation pipelines, caching
Dataset versioning: DVC or equivalent

Computer Vision Fundamentals

Strong CV fundamentals: preprocessing, geometry, photometric effects, distortions, camera models
OpenCV expertise for classical CV and integration into modern ML pipelines
Evaluation expertise: mAP, precision/recall, IoU, PR curves, calibration

Deep Object Detection Expertise

Hands-on experience with modern detectors such as: YOLO (v5/v8/v9), Faster R-CNN, RetinaNet, EfficientDet, DETR variants
Experience building advanced detection workflows:
- Multi-stage detection (proposal, refine, classify)
- Ensemble and stacking strategies
- Specialized post-processing tuned to domain constraints

Production ML and MLOps Delivery

Model export and serving: ONNX export/runtime, plus at least one of TorchScript or TensorRT
GPU inference optimization and performance tuning (batching, throughput, latency, memory)
Deployment: Docker, Linux, CI/CD basics (GitHub Actions and/or GitLab CI)
Service implementation: FastAPI and/or gRPC, model versioning, rollback strategy
Monitoring and lifecycle: drift/performance monitoring, logging, dashboards, retraining triggers
Testing: unit tests for preprocessing/post-processing, integration tests, regression sets, threshold stability tests

R&D Capability