AI Engineer

• Design, develop and maintain scalable Python applications and data pipelines using Pandas for data extraction, transformation and loading (ETL).

• Build and expose secure, well-documented REST APIs using FastAPI, applying data validation (e.g. Pydantic) and API best practices.

• Write efficient SQL and work with relational databases such as Oracle, PostgreSQL and MS SQL Server, including data modelling, query optimization and performance tuning.

• Containerize applications using Docker and support deployment across development, test and production environments.

• Develop Generative AI and Agentic AI solutions – LLM-based applications, RAG pipelines, and multi-agent workflows using frameworks such as LangChain, LangGraph or CrewAI.

• Integrate Large Language Models through provider APIs (e.g. OpenAI / Azure OpenAI) and open-source models (e.g. Hugging Face), applying prompt engineering, structured outputs and function / tool calling.

• Build natural-language interfaces to data (e.g. Text-to-SQL agents) that allow business users to query databases in plain English.

• Automate business workflows by combining AI capabilities with APIs, scheduling / workflow tools (e.g. n8n) and messaging integrations.

• Integrate AI solutions with enterprise data sources and tools, including vector databases and Model Context Protocol (MCP) based tool integrations.

• Implement LLM observability, tracing and evaluation (e.g. Langfuse) to monitor quality, cost, latency and reliability of AI applications.

• Develop, train and evaluate Machine Learning models where appropriate, using libraries such as Scikit-learn, TensorFlow and NumPy.

• Follow sound engineering practices: version control with Git, code reviews, unit / integration testing and clear technical documentation.

• Contribute to CI/CD pipelines (e.g. GitHub Actions / Jenkins) and support deployment of AI services on on-premise or cloud platforms (AWS / GCP / Azure).

• Translate business requirements into technical designs and work closely with business users, data teams and other stakeholders throughout implementation and delivery.

Contributing Responsibilities

• Contribute to the design of reusable components, frameworks and best practices for data engineering and AI development within the team.

• Ensure solutions comply with the Group’s standards on data security, privacy, Responsible AI, risk and compliance.

• Identify opportunities for automation and process improvement, and propose AI-driven solutions.

• Participate in knowledge sharing, mentoring and cross-training to build AI capabilities within the team.

• Stay up to date with the evolving AI / LLM ecosystem and assess new tools and techniques for adoption.

Technical & Behavioral Competencies

• Strong programming skills in Python, with hands-on experience in data manipulation and analysis using Pandas.

• Solid working knowledge of SQL and relational databases – Oracle / PostgreSQL / MS SQL Server.

• Experience designing and building REST APIs, preferably with FastAPI.

• Good understanding of ETL concepts, data pipelines, data quality and data integration.

• Practical experience with Docker and Git based development workflows.

• Exposure to LLM APIs (OpenAI / Azure OpenAI), Hugging Face models, prompt engineering, LLM application frameworks (LangChain, LangGraph, CrewAI), RAG pipelines, vector databases and LLM observability tools (e.g. Langfuse) is a strong plus.

• Familiarity with ClickHouse, front-end frameworks (React / Angular), Machine Learning libraries (Scikit-learn, TensorFlow, NumPy), CI/CD and cloud platforms (AWS / GCP / Azure) is an added advantage.

• Strong analytical and problem-solving skills with attention to detail; ability to communicate clearly with technical and non-technical stakeholders.