Who you are

• 5+ years in applied ML/AI (or 5+ with an advanced degree) delivering production systems in document AI/OCR/NLP or information extraction at scale
• Strong Python and deep learning expertise (PyTorch/TensorFlow), with experience in LLMs, embeddings/vector search, prompt design/evaluation, and statistical methods for quality and uncertainty
• Cloud‑native ML ops experience: training/inference pipelines, feature/data stores, observability, cost/perf optimization
• Own end‑to‑end lifecycle for AI features: design → implementation → testing → deployment → monitoring → iteration
• Optimize model/workflow inference for latency, throughput, and cost, including caching, batching, and model selection strategies
• Implement monitoring, logging, tracing, and alerting for workflows and models in production (data drift, model performance, error rates)
• Debug and troubleshoot complex AI systems in production, including prompt failures, integration bugs, and data quality issues
• Partner with Product, Tax SMEs, and other engineering teams to translate business/tax requirements into AI workflows
• Collaborate with data scientists and ML engineers on model selection, evaluation, and experimentation within Reducto pipelines
• Lead design reviews, perform code reviews, and mentor mid‑level/junior engineers on AI best practices and production‑grade coding
• Contribute to internal standards, best practices, and templates for building AI workflows with Reducto
• You've built end‑to‑end AI features that are running in production, not just prototypes
• You can take a vague tax/business requirement and turn it into a concrete, testable workflow design
• You care about robustness and correctness as much as cleverness—especially in domains where errors have financial or compliance impact
• You're comfortable reading tax/business rules and working with domain experts, even if you're not a tax specialist yourself
• Document AI background: layout parsing, table extraction, doc‑type classification, native‑PDF matching, and verification automation
• Agentic/LLM orchestration experience: familiarity with TR AI platforms such as Materia and Additive; retrieval‑augmented and tool‑use patterns; evaluation and guardrails
• Modern Development Practices: Hands-on with modern AI coding assistants including Claude Code, Cline, and GitHub Copilot for rapid prototyping, code generation, and workflow automation
• Version control: Experience with version control (Git), testing frameworks (pytest or similar), and modern DevOps practices
• Software Engineering: Familiarity with C#, Java or any other programming language
• Domain familiarity: exposure to tax/financial document workflows or other regulated content systems is a plus

What the job involves

• Are you ready to shape the future of AI‑driven tax automation
• We're looking for a Senior AI Engineer to build and scale intelligent workflows using modern LLM/ML tooling
• Your work will directly impact how tax professionals automate complex, high‑stakes processes and access critical information
• You'll join our Tax and Accounting Professionals 1040 Scan product engineering team and own the design, implementation, and optimization of AI‑powered tax workflows—from data ingestion to production deployment
• 1040SCAN is the market-leading scan-and-populate engine in the 1040 workflow, organizing workpapers, extracting data, and exporting to tax software at scale
• As a Senior AI engineer, you will modernize the AI that powers document understanding, extraction, and verification—expanding coverage and accuracy while reducing human effort
• Advance document intelligence: Build generalizable models for tax documents (standard and non‑standard) using CV/NLP/LLMs and embeddings to move beyond fixed OCR templates with dynamic, context‑aware parsing
• Boost auto‑verification & quality: Improve native‑PDF/text‑layer matching, anomaly detection, and prior‑year‑aware checks to catch issues before human review; design human‑in‑the‑loop flows that preserve practitioner control
• Scale the pipeline: Productionize low‑latency training/inference pipelines over millions of documents with robust observability, evaluation, and drift monitoring
• Integrate LLMs and traditional ML models into robust, auditable workflows that support tax determination, document processing, and rules‑based automation
• Build and maintain data pipelines, feature extraction, and preprocessing for tax‑relevant data (e.g., invoices, filings, transactional data)
• Develop and integrate RESTful APIs / microservices to expose AI capabilities to internal and external systems
• Ensure solutions meet compliance, security, and auditability requirements typical of tax and regulated domains
• You’ll collaborate across SurePrep engineering and other Thomson Reuters product & engineering teams leveraging TR’s AI platforms including Materia and Additive to deliver reliable, auditable AI in production