Opening For AI ML Engineer

Tekskills; Chennai District; On-site; INR 180,000 - 360,000; Full time

Job summary

Tekskills in Chennai seeks an AI ML Engineer to build and fine-tune OCR models, handwriting models, and document segmentation pipelines. You will implement preprocessing steps like deskew, denoise, and stamp removal, and train CV models (YOLO/SAM) for stamp and handwriting region detection.

The role involves evaluating OCR engines and creating benchmarking frameworks. You will also develop orchestration pipelines for ensemble predictions and optimize inference for high-throughput processing of

Qualifications

• Builds and fine-tunes OCR and document segmentation models.
• Implements preprocessing: deskew, denoise, remove stamps/watermarks, crop, binarize.
• Trains CV models (YOLO/SAM) for stamp and handwriting region detection.
• Evaluates OCR engines and benchmarks them.
• Builds orchestration pipelines for ensemble predictions.
• Optimizes inference for millions of documents.

Responsibilities

• Develop, fine-tune, and optimize OCR and document segmentation models.
• Implement preprocessing steps: deskew, denoise, watermark/stamp removal, cropping, binarization.
• Train CV models (YOLO/SAM) for stamp detection and handwriting region detection.
• Evaluate multiple OCR engines and build benchmarking frameworks.
• Build orchestration pipelines enabling ensemble predictions.
• Optimize inference for large-scale throughput (millions of docs).

Skills

PyTorch

TensorFlow

OpenCV

CNNs

Vision Transformers

Tools

YOLO

SAM

Job description

AI ML Engineer-Builds and fine-tunes OCR models, handwriting models, document segmentation, stamp detection, and image clean up pipelines:

Job Description:

Builds and fine-tunes OCR models, handwriting models, document segmentation, stamp detection, and image clean up pipelines.

Key Responsibilities

• Develop, fine-tune, and optimize OCR and document segmentation models.
• Implement preprocessing: deskew, denoise, watermark/stamp removal, cropping, binarization.
• Train CV models (YOLO/SAM) for stamp detection, handwriting region detection.
• Evaluate multiple OCR engines and build benchmarking frameworks.
• Build orchestration pipelines enabling ensemble predictions.
• Optimize inference for large-scale throughput (millions of docs).

Qualifications

• 38 years in CV/ML.
• Deep knowledge of PyTorch, TensorFlow, CNNs, Vision Transformers, OpenCV.
• Prior OCR/DocAI experience preferred.

Essential Skills:

• AI and Automation Engineers with Dashboarding skillset
• AI ML Engineers
• Java HPCAI Engineers