3 months ago
Pune, IndiaStaff+
Responsibilities
- Design, develop, and maintain ETL processes that extract, transform, and load data into data warehouses.
- Build and maintain Python-based data pipelines and optimize them for performance and scalability.
- Write SQL queries and PL/SQL scripts for data manipulation, validation, and transformation.
- Implement data quality checks and monitoring and troubleshoot data-related issues.
- Collaborate with data analysts and stakeholders to understand requirements and deliver data solutions.
- Design, deploy, and integrate agentic AI systems, including Model Context Protocols and LLM-based services.
- Develop robust APIs and scalable enterprise solutions using microservices, event-driven architectures, and API-first design.
- Create and maintain technical documentation for ETL processes, data pipelines, database solutions, and AI systems.
- Ensure application resiliency, security, testing, version control, code review, and operational stability for AI initiatives.
Requirements
- At least 10 years of hands-on application development experience.
- Expert-level proficiency in Python and experience with FastAPI, Flask, or PySpark.
- Strong knowledge of databases including Oracle, MySQL, SQL, PostgreSQL, or MongoDB.
- Hands-on experience with ETL, data pipelines, data warehouses, application and data architecture, and scalable enterprise solutions.
- Knowledge of AI concepts including knowledge representation, automated planning, decision-making under uncertainty, and multi-agent systems.
- Experience with AI frameworks such as Google ADK, LangGraph, LangChain, AutoGen, CrewAI, or N8N.
- Proven experience creating, deploying, and integrating Model Context Protocols into agentic AI systems.
- Familiarity with large language models including ChatGPT, Claude, Gemini, and Llama and their use in agentic systems.
- Experience designing and implementing APIs for AI services.
- Experience with Git, CI/CD pipelines, comprehensive testing, code reviews, agile methodologies, application resiliency, and security principles.
- Experience with Docker and OpenShift.
- Machine learning framework experience with TensorFlow or PyTorch and libraries such as Scikit-Learn, NumPy, or Pandas is preferred.
Tech Stack
Categories
AI ApplicationsData Engineering
About Citi
Citi is a public financial-services company offering consumer and institutional banking, credit cards, wealth management, treasury and trade solutions, and capital-markets services. It serves individuals, corporations, financial institutions, and governments in more than 160 countries and jurisdictions, earning interest and fee income from lending, payments, trading, and advisory. Founded in 1812 and headquartered in New York, it trades on the NYSE under the ticker C.