Jimmy Technologies

• Develop and maintain scalable back-end services. • Design and build the architecture behind the AI systems, developing robust agentic workflows, MCP servers, and scalable integrations between LLMs and our backend infrastructure. • Ensure seamless integration with front-end applications and external services through well-designed RESTful APIs. • Leverage cloud infrastructure (Azure Functions, Azure Storage) for hosting and scaling applications. • Implement security best practices for API authentication (OAuth, JWT) and data protection. • Possibly work on GenAI-driven applications, utilizing AI APIs. • Containerize applications using Docker for environment management.

• Develop and maintain scalable back-end services using FastAPI and other modern frameworks. • Ensure seamless integration with front-end applications and external services through well-designed RESTful APIs. • Maintenance of integration modules in Node.js/React that connect the frontend to Python APIs. • Contribute to Node.js backend components when required, integrating them with Python services. • Leverage cloud infrastructure (Azure Functions, Azure Storage) for hosting and scaling applications. • Implement security best practices for API authentication (OAuth, JWT) and data protection. • Work on GenAI-driven applications, utilizing frameworks such as LangChain, LlamaIndex, vector databases, and agentic frameworks. • Containerize applications using Docker for environment management.

• Design and develop scalable data pipelines, backend services, and APIs. • Build knowledge graph solutions, including graph data modeling, relationship mapping, and graph traversal logic. • Build ETL pipelines. • Design data models. • Implement GraphRAG solutions combining knowledge graphs, vector search, metadata, and LLM-based retrieval. • Create Source to Target Mappings (STMs) for ETL specifications. • Implement automated ingestion patterns, incremental (delta) updates, and streaming/CDC workflows. • Gather requirements, set targets, define interface specifications, and conduct design sessions. • Work closely with data consumers to ensure proper integration. • Adapt and learn in a fast-paced project environment.

• Data Modeling & ETL Development • Build ETL pipelines • Design data models. • Design and implement GraphRAG solutions combining knowledge graphs, vector search, metadata, and LLM-based retrieval. • Create Source to Target Mappings (STMs) for ETL specifications. • Implement automated ingestion patterns, incremental (delta) updates, and streaming/CDC workflows. • Collaboration & Agile Development • Gather requirements, set targets, define interface specifications, and conduct design sessions. • Work closely with data consumers to ensure proper integration. • Adapt and learn in a fast-paced project environment.

• Develop and maintain backend services using Node.js and Typescript. • Develop and maintain frontend application using React / Vite. • Perform code reviews and ensure high-quality coding standards. • Define and evaluate best practices for software development. • Implement design patterns and explain their value in the development process. • Collaborate with cross-functional teams to drive efficient and innovative solutions. • Work in an Agile environment, planning work daily and proactively addressing blockers. • Utilize Azure DevOps and Git for source control and CI/CD pipelines.

• Design and implement scalable, repeatable deployment frameworks for AI, data, and cloud-native applications. • Develop and maintain Infrastructure as Code (IaC), automated environment provisioning, and deployment workflows to ensure consistency across environments. • Build and optimize CI/CD pipelines that enable reliable, automated delivery across development, testing, staging, and production. • Standardize application packaging and deployment models to enable seamless delivery into customer environments with minimal customization. • Define and implement best practices for secrets and configuration management, identity and access management (IAM), networking, secure connectivity, observability, logging, monitoring, alerting, and release management. • Improve production readiness by strengthening application resilience, scalability, security, runtime governance, and operational excellence. • Observability Improvements: Enhance monitoring for services to improve system reliability. • Scripting & Automation: Develop, implement, and maintain scripts to automate processes and reduce manual efforts.

• Implement orchestration, retrieval pipelines, and validator agents using graph-aware tools. • Build hybrid search pipelines (lexical + vector) and integrate vector databases like FAISS, Milvus, or Pinecone. • Integrate LLMs (Azure OpenAI, Anthropic) and support domain-specific fine-tuning or adapter models. • Develop robust API endpoints and ETL pipelines to support model and agent runtimes. • Create evaluation suites for reliability, drift detection, and performance optimization.

• Develop and maintain native Android applications using Kotlin • Participate in application design and technical architecture discussions • Implement new features and improve existing functionality • Collaborate with backend developers and other stakeholders • Perform code reviews and ensure code quality • Troubleshoot and resolve technical issues • Contribute to the continuous improvement of the development process

• Architect Foundry Pipelines: Design, develop, and maintain scalable data pipelines within the Palantir Foundry ecosystem (Data Connection, Code Repos, Pipeline Builder). • Implement ETL processes: Implement ETL and real-time data pipelines for efficient data handling and integration. • Optimize PySpark: Write and tune high-performance Python/Spark code to transform massive insurance datasets into actionable insights. • Build the Ontology: Manage and scale the Foundry Ontology, ensuring data models accurately represent complex real-world insurance entities. • Implement AI/GenAI: Integrate GenAI capabilities (using Palantir AIP or external AI APIs) to automate workflows and enhance data enrichment. • Implement CI/CD: Implement practices using CodePipeline and CodeBuild to streamline development and deployment processes. • Collaboration & Agile Development: Gather requirements, set targets, define interface specifications, and conduct design sessions. Work closely with data consumers to ensure proper integration. Adapt and learn in a fast-paced project environment.