Skills required
- Python FastAPI — async endpoints, dependency injection, Pydantic v2
- LLM API integration — OpenRouter, Claude Sonnet, structured prompting for clinical entity extraction:
- LangChain — chains, prompt templates, output parsers, provider abstraction
- Document parsing — PyMuPDF (PDF), python-docx (DOCX), openpyxl (XLSX):
- Pydantic v2 — typed schema validation, custom validators, serialization
- Tavily API or equivalent search API integration:
- Async Python — async/await, background tasks, FastAPI lifespan
- Docker, GitHub Actions CI/CD:
- pytest and pytest-asyncio for pipeline testing

Required Qualifications
- 3-5 years in Python backend with at least one production LLM integration




- Experience building data extraction or NLP pipelines from unstructured documents
- Clinical, life sciences, or regulated domain experience is a robust advantage
- Ability to define and measure extraction quality — not just build the pipeline but validate it

Stack
- Python 3.11+
- LangChain
- OpenRouter
- Claude Sonnet
- PyMuPDF
- python docx
- openpyxl
- Pydantic v2
- Tavily
- Docker
- GitHub Actions
- pytest,FastAPI

Pay: ₹170,000.00 - ₹200,000.00 per month

Work Location: In person

📌 Ai Engineer 1 (Noida)
🏢 Scaleupally
📍 Noida