Software Developer (Resume Parsing - NLP, ML, OCR)

Delhi - India

Monthly Salary: Not Disclosed

Posted on: 30+ days ago

Vacancies: 1 Vacancy

The job posting is outdated and position may be filled

Job Summary

Role Overview: We are seeking an experienced Software Developer to design and implement a resume parsing system capable of extracting structuring and classifying candidate information (education skills experience certifications etc.) from diverse CV/resume formats (PDF Word LinkedIn profiles scanned docs). The developer will leverage NLP OCR and ML models to deliver an accurate scalable and API-driven solution that integrates seamlessly with ATS/HRMS platforms.

Key Responsibilities:

System Development & Design :

Develop parsing engines to accurately extract candidate details (contact info skills education work history projects achievements).
Handle diverse file formats (DOCX PDF TXT scanned images).
Build scalable APIs/services for integration with ATS and job portals.

NLP & Data Processing :

Implement NLP techniques for named entity recognition (NER) semantic analysis and skill extraction.
Apply regex/rule-based methods alongside ML models to handle edge cases.
Normalize and structure extracted data into formats like JSON/XML for easy consumption.

ML/OCR Integration :

Integrate OCR solutions (Tesseract AWS Textract Google Vision) for image-based resumes.
Train/fine-tune ML/NLP models (SpaCy Hugging Face Transformers Scikit-learn) for improved parsing accuracy.
Continuously enhance parsing models with feedback loops and dataset improvements.

Testing CI/CD & Deployment

Ensure high parsing accuracy with automated test suites and validation pipelines.
Design and manage CI/CD pipelines (Jenkins GitHub Actions GitLab CI or similar).
Containerize using Docker/Kubernetes for scalable deployment.
Deploy solutions on AWS/GCP/Azure with monitoring & logging.

Collaboration & Documentation

Collaborate with product data and QA teams for seamless ATS/HRMS integration.
Write clean modular and well-documented code.
Prepare technical documentation workflows and API reference guides

Key Skills & Competencies :

Strong programming skills in Python (preferred) or Java/C#.
Experience with NLP frameworks (SpaCy NLTK Hugging Face BERT/transformers).
Knowledge of resume data structures (HR-XML JSON Resume etc.).
Proficiency in regex & text preprocessing techniques.
Experience with OCR libraries/tools.
Familiarity with ML frameworks (PyTorch/TensorFlow).
Database knowledge (SQL/NoSQL).
Strong grasp of REST API development.
CI/CD pipelines & cloud deployment desirable /can be learnt

Education & Experience:

B.E/ /MCA or related field.

2-5 years of experience in software development with a focus on NLP/Resume Parsing/ATS-related applications.
Prior experience in building or working with resume parsers ATS or HR tech platforms is a strong plus.

Soft Skills :

Analytical mindset with strong attention to detail.
Ability to handle edge cases across diverse resume formats.
Team player with strong communication skills.
Innovative thinker with problem-solving orientation

Develop parsing engines to accurately extract candidate details (contact info skills education work history projects achievements).
Handle diverse file formats (DOCX PDF TXT scanned images).
Build scalable APIs/services for integration with ATS and job portals.