Generative AI Engineer

Hiring: AI Engineer
Experience: 5–7 Years
Shift: EST
Work Mode: Remote/Hybrid
Role Overview
We are looking for an AI Engineer with strong Python backend development and hands-on experience building document intelligence, local LLM, and retrieval-based systems. The role focuses on self-hosted AI solutions, Azure integrations, and AI-assisted development for mission-critical applications.
Mandatory Tech Stack
Python 3.11+ – Async, typing, Pydantic v2, pytest
FastAPI – Microservices and API development
SQLAlchemy, Alembic, PostgreSQL, Redis
Docker, Poetry, Git, CLI
Azure – Key Vault, Blob Storage, Entra ID
Document Processing – OCR, layout analysis, structured data extraction
Local LLMs, Embeddings, Vector Search, RAG
Windows/PowerShell and Linux deployment knowledge
AI coding agents – Task decomposition, code generation, critical review, and debugging
Nice to Have
Tesseract OCR internals and chunking strategies
Microsoft Graph, Fabric, and Databricks
Tkinter or desktop UI development
FinTech, banking, or financial services experience
Key Responsibilities
Develop and maintain Python/FastAPI microservices.
Build document extraction, confidence scoring, and predictive matching workflows.
Integrate self-hosted models, embeddings, and vector search without metered AI APIs.
Implement Azure integrations, automated testing, CI gates, and release processes.
Use AI coding agents to accelerate development while ensuring code quality and production readiness.
Important: Candidates must have strong Python backend fundamentals, practical AI/document-processing expertise, and the ability to review and ship reliable, production-grade code in an AI-first development environment.
Interested candidates can share their updated CVs for review.

Work arrangement
Yes