• Develop and maintain applications using Java 8 (or similar) and jQuery . • Build and enhance solutions with Oracle Commerce products , specifically: ATG Web Commerce 11.4 Endeca Commerce 11.4 Oracle Secure Enterprise Search 11.4 • Provide application support, including but not limited to: Querying and analyzing database information to produce requested reports. • Deploying environments on web and application servers. • Performing load and performance testing. • Managing certificates and overseeing server health monitoring.

• Design, implement, and operate scalable distributed systems in production. • Build low-latency and streaming systems for real-time and near real-time workloads. • Develop data pipelines and ETL workflows for ingesting, transforming, and serving data. • Build and maintain application services and APIs used by internal and external systems. • Implement Web3 protocol integrations, including smart contract interactions and on-chain data ingestion via RPCs, logs, and indexers. • Apply SRE principles to improve reliability, observability, and operational correctness. • Participate in incident response, debugging production issues and driving root-cause fixes. • Contribute to system design and code reviews, maintaining high engineering standards. • Leverage AI-assisted development tools to improve productivity, code quality, and system understanding, while exercising strong engineering judgment. • Write and maintain technical documentation for systems and workflows.

• Develop and deliver full-stack AI-powered applications on top of Unframe’s platform. • Work closely with customers and internal teams to tailor solutions. • Extend the platform and UI/UX layer as needed. • Collaborate with platform and research teams to integrate AI capabilities into production use. • Write clean, tested, and maintainable code.

• Build and support AI agents and orchestrators on an agentic AI platform powered by Semantic Kernel • Develop and integrate MCP servers and tools using Python FastMCP (core responsibility) • Implement multi-agent workflows (sequential, parallel, and handoffs) with guidance from senior engineers • Design and iterate on prompts and prompt strategies to improve quality and reliability • Contribute to building and maintaining LLM evaluation (eval) pipelines • Integrate LLM providers via APIs/SDKs and support experimentation • Help build RAG pipelines using vector stores and retrieval frameworks • Instrument systems using observability tools like Langfuse for tracing and cost monitoring • Write clean, testable, and maintainable Python code • Participate in code reviews, debugging, and testing • Support CI/CD and deployment workflows • Continuously learn and apply best practices in agentic AI development