About this role
About the RoleWe are building a production-grade, AI-enabled tax compliance platform to support the preparation of 5,000+ tax returns annually and enhance our existing workflows through structured automation and AI-assisted processing. This platform is designed to support and augment our tax teams, reducing time spent on repetitive data preparation while enabling greater focus on review, judgment, exception handling, and client advisory work. By improving efficiency and consistency across processes, the system will empower both our local and offshore teams to deliver higher-quality outcomes and scale effectively as volumes grow. This is a high-impact engineering role focused on building an end-to-end AI-assisted system that will play a key role in modernizing how our firm operates, while keeping human expertise at the core of decision-making. You will take end-to-end technical ownership of a business-critical system, leading design and delivery from architecture through to production deployment. You will work closely with tax and domain experts to translate regulatory and business requirements into scalable, production-grade system logic. Note: This is a production-grade system build (not a prototype or chatbot use case). The system must be reliable, auditable, and designed to work alongside professional reviewers in a controlled, compliance-driven environment. What You Will BuildThe system is designed around review-first, exception-based workflows, where routine, standardized cases are pre-prepared to a high level of accuracy, allowing professionals to focus on validation, exceptions, and advisory judgment. Key capabilities include: Document Ingestion • Automatic retrieval of tax-related documents from document management systems • Support for documents such as income statements, payroll records, contribution statements, and supporting documents • No manual uploading required AI Data Extraction • Use LLM-based workflows to extract, validate, and structure financial data • Convert unstructured documents into structured datasets Reconciliation Engine • Cross-check data across multiple sources • Detect inconsistencies, missing elements, and anomalies AI-Assisted Case Preparation • Generate structured, review-ready cases with flagged issues and summaries • Provide draft tax positions for reviewer validation • Produce clear, plain-English summaries for efficient review Final tax calculations will be handled by a deterministic, rule-based engine. AI is used to support extraction, validation, anomaly detection, and explanation—not to replace professional judgment. Workflow Automation • Pre-process standard cases • Highlight and escalate exceptions • Enable structured review workflows and tracking Key ResponsibilitiesAI & Backend Development • Build multi-step LLM workflows (extraction, validation, reconciliation, summary) • Design structured data schemas • Implement prompt pipelines with validation layers • Develop confidence scoring and fallback mechanisms Integration & Data Pipelines • Integrate with document management systems • Build ingestion and classification pipelines • Process PDFs, scans, and structured inputs System Development • Build backend services (Python, FastAPI preferred) • Develop internal dashboards for tracking, issue management, and workflows Tax Logic Integration • Build or integrate deterministic tax rules • Ensure outputs are auditable and structured Security & Compliance • Ensure data protection compliance • Implement role-based access control • Maintain audit trails RequirementsMust-Have • 3–6 years of backend or AI engineering experience • Strong Python experience (FastAPI preferred) • Experience building multi-step LLM pipelines with validation layers in production • Experience with document processing and structured data extraction • Strong understanding of APIs, JSON, and data flows • Ability to design end-to-end data pipelines Good to Have • Experience with financial, tax, or payroll data • Experience with workflow automation systems • Familiarity with document systems (e.g. M-Files, SharePoint, S3) • Experience with PDF parsing tools DeliverablesMVP (10–12 weeks) • End-to-end flow: ingestion, extraction, structured dataset, basic summaries • Production-ready with validation, logging, and error handling Full System (6 months) • Reconciliation engine • Exception workflows • Reviewer dashboard • Audit and logging framework
Also in Software Engineering
RAPSYS TECHNOLOGIES PTE. LTD.
ANRADUS PTE. LTD.
SUNNYHILL ACE PTE. LTD.