Role Description As a Fullstack AI Engineer, you will play a key role in the full development lifecycle of a high-impact Generative AI MVP, translating complex architectural requirements into technical solutions. You will be responsible for building the bridge between Azure AI Foundry agents and the end-user, developing robust APIs, integrating RAG (Retrieval-Augmented Generation) pipelines, and implementing a simplified frontend. Beyond technical execution, you will collaborate closely with an AI Specialist and stakeholders to ensure the delivery of an explainable and compliant solution within an Agile framework. Responsibilities and Duties - Digest requirements from the architecture and product team to specify the implementation of new features from a fullstack and AI-integration perspective. - Implement the designed solution from coding to testing, focusing on Azure Functions, API development, and agentic workflows. - Follow Agile processes and participate actively in all development phases to ensure a functional MVP within 3 months. - Development of new features, including data connectors for Excel/Word and tool orchestration for LLM agents. - Design and maintain the application's frontend to provide a seamless interface for "Well Engineers". - Participate in the complete cycle of development from requirements gathering, RAG data ingestion, to final deployment. - Participate in technical discussions, demonstrations, and reviews with customers (Halliburton/Petrobras context). Qualifications - Solid Experience with Python (preferred) or Node.js. - Frameworks: ReactJS for frontend development. - AI Integration: Experience with LangChain, Semantic Kernel, or similar LLM orchestration frameworks. - Cloud Knowledge: Solid experience with Azure (Functions, App Service, and Blob Storage). - API Development: Experience with REST APIs and integrating third-party AI services. - Data Handling: Experience processing structured and unstructured data (Excel/Word) for AI consumption. - Solid experience with Git. Highly Desirable Skills - Experience with Azure AI Foundry and Azure AI Search. - Knowledge of Vector Databases and RAG architectures. - Experience with automated testing (Unit, Integration) for AI-driven applications. - Familiarity with AI Observability tools (Tracing, Prompt Logging). - Experience with Tailwind CSS or fast prototyping UI libraries. - Knowledge of Docker and CI/CD pipelines within Azure DevOps. Posted On May 20, 2026 Company Description At Coforge, we hire professionals based solely on their skills and do not discriminate based on age, disability, religion, gender, sexual orientation, socioeconomic status, or nationality.

• Design, build, and own end-to-end applications that support credit, private credit, structured products, and CLO businesses • Write production code across the stack, model financial cash flows and risk, integrate market data and pricing services, and partner directly with client solutions group, portfolio managers, risk, operations, and investor relations • Contribute to the modernization of the analytics and reporting platform - moving legacy applications to responsive, cloud-aware architecture • Replace ad-hoc spreadsheets with auditable services, and build the data and tooling layer that supports the firm’s various lines of business • Use AI coding assistants as a daily part of your workflow

• Build full-stack applications across our credit, private credit, and structured products platforms — backend services, APIs, data pipelines, and modern web front ends used by various business teams across the firm • Integrate third-party systems including Geneva (portfolio accounting), market data vendors, CRM platforms, and administrative platforms, design clean, well-tested adapters and reconciliation logic. • Participate in the Migration of legacy .NET/C# applications and SSRS reports to modern, scalable architectures (TypeScript/React front ends, Python or .NET services, cloud-deployed) with responsive UX across desktop and mobile. • Own data quality end-to-end - ingestion, normalization, validation, and lineage - for firmwide positions, partnering with the data management team on governance and controls. • Build reporting and BI spanning Tableau dashboards, internal web tooling, investor reporting, and ad-hoc requests for portfolio composition and DDQ responses. • Translate business needs into engineering — gather requirements directly from PMs, analysts, risk, IR, and operations; document functional and technical specs; write clear UAT plans and lead testing. • Ship like an engineer - write tests, use source control (GIT/TFS), open clean PRs, manage tickets in DevOps, deploy through CI/CD, and monitor what you ship in production. • Use AI coding assistants well - accelerate delivery, reduce boilerplate, and improve code quality, while applying the verification, security, and review standards described later in this document. • Approximate Time Allocation • 60% development — services, APIs, front-end, integrations • 20% reporting and dashboard development — Tableau, SQL, internal web tooling • 15% requirements gathering, analysis, and UAT • 5% production support and code review

• Design, develop, and deploy production-grade AI/ML and Generative AI solutions • Build and optimize RAG pipelines, embeddings, semantic search, and document intelligence workflows • Develop scalable APIs and full-stack applications supporting AI use cases • Collaborate closely with system architects across the full software lifecycle • Implement LLM evaluation frameworks, monitoring, and performance metrics • Apply AI safety guardrails including content moderation and hallucination reduction • Lead and mentor engineers through design, development, testing, and release cycles • Communicate technical tradeoffs and progress clearly to stakeholders