Proficient in Python programming with strong understanding of object-oriented programming concepts.
Extensive experience with data manipulation libraries such as Pandas and NumPy ensuring clean, efficient, and maintainable code.
Develop and maintain real-time data pipelines / microservices to ensure seamless data flow and integration across systems.
Working knowledge of Python packaging, virtual environments (venv/Poetry), and dependency management.
SQL:
Strong understanding of basic SQL query syntax, including joins, WHERE, and GROUP BY clauses.
Good-to-Have Skills:
Python
Practical experience in AI development application.
Experience with parallel processing and multi-threading/multi-processing to optimize data fetching and execution times.
Familiarity with SQLAlchemy or similar libraries for data fetching.
Handson experience with at least one LLM framework (LangChain, LangGraph, or similar) and OpenAI compatible APIs (Azure OpenAI / Gartner models).
Others:
Experience with cloud native and serverless architectures on AWS: Lambda, API Gateway, S3, CloudWatch; exposure to EC2, RDS/Postgres (including pgvector), EKS, or Batch is a plus.
Knowledge of observability practices (structured logging, metrics, tracing) for debugging and operating distributed LLM/RAG/agent systems in production.
Key Responsibilities:
Develop and maintain Python applications with a focus on API building, data processing, and transformation.
Utilize LangGraph to design and manage complex language model workflows. Work with machine learning and text processing libraries to deploy agents.
