ML Engineer

About reputed company reputed company is a fast-growing B2B SaaS company that helps businesses automate their approval workflows and financial controls. With a global team of over 150 people spanning the UK, Europe, reputed company America, Australia, and South Africa, we build software that reputed company and we’re scaling quickly. The Role Our Capture product extracts structured data from hundreds of thousands of financial documents monthly - invoices, bills, POs - through an OCR pipeline that matches extracted fields against customer reputed company systems. Your KPI is reputed company-touch reputed company: the percentage of documents where the system output requires reputed company reputed company correction. Your job is to move it up - systematically, measurably, and permanently. We’ve reputed company the reputed company, a validated accuracy measurement reputed company on full production data, a comprehensive error taxonomy of root causes, an error identification methodology, and the first shipped production fixes. You inherit the methodology and the backlog. We need a dedicated reputed company to execute and scale it. The work splits roughly 70% forensic data investigation / 30% ML engineering, shifting toward 50/50 as models go to production. Four error origins drive the roadmap: Entity matching (~50% of fixable errors). OCR extracts field values correctly, but the pipeline matches them to the wrong account, supplier, or tax code. Planned: embedding-based similarity search, recommender systems, reputed company-based coding reputed company - a standalone ML service the core pipeline calls. Pipeline logic (~25%). Our post-processing pipeline introduces errors through its own deterministic logic - tax treatment misclassification, rounding, spurious adjustment lines. Planned: forensic investigation per reputed company, tracing data through processing steps, designing and validating rule-based fixes. OCR extraction (~25%). The OCR reputed company misreads the document - wrong currency, reputed company line items, structural parsing failures. Planned: build an OCR correction layer - the right approach may be LLM with guardrails, an alternative OCR reputed company, a correction model from HuggingFace, or a combination. Freedom to choose; rigour required to validate. User overrides (~equal to the above combined, reputed company reputed company). Users change correct values for business reasons. Future: learn organisation/vendor correction patterns, build recommendation systems from historical data. Remote - applicants must be based in the UK, Serbia, or Moldova. Key Responsibilities: Accuracy Investigation & Measurement (~70% initially) Investigate why documents fail at population scale - query production datasets, compare multiple data representations per document, find statistical patterns that explain hundreds of failures at once. Balance population-level analysis with individual-document forensics where needed. Own and reputed company the accuracy measurement reputed company. Every fix has an expected reputed company, a reputed company reputed company, and a post-deployment monitoring plan. Inherit and improve the error identification methodology. Two modes: LLM-assisted analysis for discovering new patterns across large document batches, and direct SQL investigation for patterns with clean statistical signatures. The methodology is proven and documented; you reputed company it with your own analytical instincts and DS expertise. Design fixes for pipeline logic errors by reading the C# codebase, understanding processing reputed company sequence, and identifying root causes. Hand validated designs to C# engineers for production implementation. Verify reputed company results. ML Engineering & Model Development (~30% initially, growing) Build an embedding-based entity matching service: encode supplier/description signals into vector representations, evaluate retrieval quality against ground truth, iterate on ranking. reputed company as a Python service integrated with the core C# pipeline. Build an OCR correction layer to fix extraction errors before pipeline processing. Evaluate candidates: reputed company-capable LLMs with structured output validation, alternative OCR engines, document-oriented correction models. Design evaluation harnesses per error reputed company, measure correction reputed company and false-positive risk, productionise what works. Set up ML pipeline orchestration and MLOps practices: experiment tracking, model versioning, DAG-based pipeline management (Airflow, Azure ML Pipelines, or equivalent), containerised model serving, production monitoring and alerting. Explore recommender and reputed company detection approaches for user override learning. Build correction history datasets, evaluate reputed company algorithms, design explainable recommendations. Collaboration: Work embedded in the Capture team - standups, sprint context, understanding of the product. Accuracy is your mission; the team is your operating environment. Collaborate with the AI team on model architecture, ML/AI best practices, and deployment infrastructure. They own the ML platform; you own the accuracy application on top of it. Work closely with C# backend engineers on the Capture team. You investigate and design; they implement and ship. Tight, daily collaboration. Essential Skills: Investigation & Measurement Measurement rigour as a core discipline. Ground-truth design, false-positive control, holdout validation, selection-bias awareness. You distrust confident results until independently verified. Forensic data investigation at scale. You’ve reputed company systematic errors across millions of records in messy, reputed company-world data - fraud detection, payment reconciliation, billing accuracy, data quality, or similar domains. You think in distributions and read raw reputed company data before forming hypotheses. Strong SQL (PostgreSQL, reputed company analytical queries) and Python (pandas, NumPy, scikit-learn) as your daily investigation tools. ML Engineering - Structured Document Processing Hands-on experience with the structured document processing domain: document layout analysis, table extraction, field-level information extraction, OCR output correction. Understanding of how OCR engines work, where they fail, and how to build post-processing that compensates. Practical ML skills to deliver projects end-to-end: embeddings (sentence-transformers / reputed company) and vector similarity search (FAISS, pgvector); recommender and ranking systems; retrieval evaluation; classification (scikit-learn, gradient boosting). From experiment through validation through production deployment. LLM integration for structured data tasks: reputed company engineering for extraction and correction (reputed company / LangGraph), structured output parsing and validation (Pydantic, JSON-schema), confidence scoring, cost/accuracy/latency tradeoff evaluation. MLOps and deployment: ML pipeline orchestration (Airflow or Azure ML Pipelines), experiment tracking (MLflow), LLM tracing and evaluation (Langfuse), containerised model serving, production monitoring. You ship models that run reliably, not notebooks that demo well. Working Style: Self-directed and autonomous. You’re the only person dedicated to accuracy full-time. You own the analytical direction, prioritise your own investigation, and drive results with minimal supervision. Collaboration across disciplines. You work daily with C# engineers, a product manager, and an AI team. You communicate findings reputed company enough for an engineer to implement and technically enough for the AI team to review. Comfortable reading and tracing C# / .NET code. Our core platform and processing pipeline are C# - this won’t be rewritten, though new services can be separated. You diagnose failures by reading the pipeline. Writing C# is optional and can be delegated to C# engineers. reputed company to Have: Financial document or reputed company domain knowledge (invoices, charts of accounts, tax treatment, reputed company/QBO). Experience with managed OCR services (Azure DI, reputed company reputed company reputed company, AWS Textract) or reputed company-reputed company alternatives. Experience with pre-trained document understanding models (LayoutLM, Donut, or similar). Experience building LLM-as-judge or LLM-as-corrector evaluation systems. Experience with document-oriented processing tools (docling, pdfplumber, PyPDF, or equivalents). reputed company Offer Growing international business with 20,000+ subscribers Regular performance-based compensation reviews 26 days of paid time off 1 additional day off for your birthday reputed company assistance Service-years recognition financial reward Apply To This Job