About the Job
Key responsibilities:1. Build and maintain web scrapers for government procurement portals, project databases, and news sites (India + global).
2. Ensure scrapers run reliably with proper error handling, logging, and configuration.
3. Transform messy, unstructured data into clean, structured tables.
4. Follow internal data standards for projects, tenders, entities, locations, sectors, contract values, and timelines.
5. Use GenAI models (via APIs) to extract structured fields from PDFs, raw text, and semi-structured documents.
6. Classify projects/tenders into sectors and categories.
7. Normalize entity names, locations, and metadata.
8. Implement basic data quality checks (duplicate detection, missing value validation, schema consistency).
9. Push cleaned and standardized data into PostgreSQL, OpenSearch, and internal APIs.
10. Coordinate with the engineering team to ensure smooth data pipeline operations.
11. Write clean, well-structured Python code with clear comments, configuration files, and logging.
12. Maintain version-controlled scripts and modules.
13. Collaborate with product and research teams to test new LLMs or extraction approaches.
14. Compare outputs, measure accuracy, and share insights.
15. Own real modules within Taiyō’s production data mesh.
16. Work under mentorship from senior engineers and economists while delivering production-grade outputs.
Number of Openings
3 openingsPerks of this Jobs
5 days a week
Skills
Python, Selenium, Machine Learning, REST API, Data Extraction, Generative AI Development, Python Libraries
Similar Job Programs
Cinematographer Job in Chandigarh at Autobott Services
Autobott Services
Stipend
INR 200000-400000 /year
Apply By
22 December, 2025
Experience
1 years
Working
full time
Business Development Executive Job in Mumbai at Upstep Academy
Upstep Academy
Stipend
INR 300000-384000 /year
Apply By
22 December, 2025
Experience
Fresher
Working
full time
Business Development Associate Job in Mumbai at Zell Education
Zell Education
Stipend
INR 950000- /year
Apply By
22 December, 2025
Experience
Fresher
Working
full time
Human Resources (HR) Associate Job in Bangalore at EDU TANTR
EDU TANTR
Stipend
INR 200000-240000 /year
Apply By
22 December, 2025
Experience
1 years
Working
full time
