Software Engineer II

The Core Infrastructure Compute team is responsible for managing and maintaining enterprise compute inventory, integrating and consolidating data from multiple sources, and ensuring data accuracy, consistency, and visibility across infrastructure platforms. The team focuses on developing modern web applications, building scalable data integration and reporting solutions, leveraging Generative AI capabilities, and delivering actionable insights through advanced analytics and intelligent automation to drive operational efficiency, informed decision-making, and continuous infrastructure optimization.

We are seeking an experienced Senior Software Engineer with strong hands-on expertise in Microsoft Power BI, MS SQL Server, React.js, Python, Generative AI, Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), vector databases, and data analytics.

The ideal candidate will possess strong software engineering fundamentals, programming expertise, analytical problem-solving capabilities, and practical experience designing and developing AI-enabled enterprise applications. The role requires the ability to integrate structured and unstructured enterprise data with modern AI technologies while ensuring application scalability, security, reliability, and performance.

Required Experience & Technical Skills

- 3-5 years of overall IT, software engineering, application development, or data analytics experience, with hands-on experience in modern application development and AI technologies.
- Strong hands-on experience with Microsoft Power BI, including DAX, Power Query, semantic modeling, dashboard development, and Power BI Service.
- Extensive experience with MS SQL Server and T-SQL, including complex queries, stored procedures, views, database design, and performance optimization.
- Strong hands-on expertise in React.js, JavaScript, TypeScript, HTML, and CSS.
- Strong programming experience in Python, including API development, automation, data processing, and integration.
- Solid understanding of software engineering principles, data structures, algorithms, object-oriented programming, and design patterns.
- Hands-on experience developing Generative AI and LLM-powered applications.
- Practical knowledge of Retrieval-Augmented Generation (RAG) architecture, implementation, and optimization.
- Experience working with vector databases such as Pinecone, Milvus, Weaviate, Chroma, FAISS, or pgvector.
- Understanding of embeddings, semantic search, vector similarity, document chunking, retrieval strategies, and context augmentation.
- Experience with LangChain, LlamaIndex, or equivalent LLM application frameworks.
- Experience integrating LLM APIs, REST services, enterprise databases, and frontend applications.
- Strong understanding of data analytics, data modeling, data transformation, and reporting solutions.
- Experience with Git, CI/CD pipelines, automated testing, and Agile software development practices.
- Knowledge of secure application development, data privacy, authentication, authorization, and enterprise AI governance.
- Strong analytical thinking, debugging, troubleshooting, and problem-solving capabilities.
- Ability to independently design, develop, deploy, and support enterprise-grade software and AI-enabled solutions.

Preferred Qualifications

- Knowledge of data warehousing, dimensional modeling, and enterprise data governance.
- Experience building AI-powered dashboards, conversational analytics, or natural-language interfaces for enterprise data.
- Experience developing applications in large-scale, highly regulated environments.