Location: Vadodara, Gujarat

Job Type: Internship (Six months of Internship tenure with Stipend)

Department: IT

Shift: General

Role Overview:

Work on real-world AI systems spanning data extraction, LLMs, RAG pipelines, and agent-based workflows.
Ideal for students who want hands-on exposure to production-grade AI engineering, not just notebooks or demos.
You will contribute to a single evolving product that starts as an MVP and is upgraded to a senior-level AI system.

Responsibilities:

- Build backend-first AI features using Python APIs
- Develop OCR pipelines for PDFs and images (credit card statements, receipts)
- Extract structured data (vendor, date, amount, transaction reference) from unstructured documents
- Implement intelligent matching logic between credit card transactions and receipts using:
- Deterministic rules (amount/date)
- Semantic similarity (embeddings)
- LLM-based validation (with strict constraints, no hallucinations)

- Assist in building RAG pipelines to enable:

- Natural language search over expense data
- Chat with data features using safe query-to-SQL patterns





- Contribute to AI agent workflows (flight selection, hotel recommendation, policy enforcement)
- Implement human-in-the-loop correction workflows and feedback-driven learning
- Write clean, testable, production-quality code
- Assist with containerization and deployment (Docker, AWS)
- Participate in end-to-end feature development: design implementation testing deployment.

Must Have:

- Strong foundation in Python
- Basic understanding of Machine Learning / NLP concepts
- Knowledge of SQL (queries, joins, aggregations)
- Familiarity with REST APIs (building and consuming)
- Git version control
- Ability to read documentation and learn independently
- Robust problem-solving mindset

Good to Have:

- Experience with OCR tools (Tesseract, OpenCV)
- Exposure to LLMs, embeddings, or RAG
- Familiarity with Hugging Face / PyTorch
- Basic understanding of Docker
- Interest in AI agents or automation workflows
- Exposure to AWS or cloud concepts

📌 AI/ML- Data Science Interns (Six months of paid Internship - Vadodara)
🏢 Si2 Tech
📍 Vadodara