Senior AI Engineer
.Monks Technology Services, part of Media.Monks and S4 Capital, is a global consulting firm mastering AI-powered transformations for the Fortune 100. We combine long-term strategic thinking, deep enterprise experience, and a human-centered approach to help clients transform business processes and dominate their industries.
About the Role
As an AI / Parsing Engineer, you’ll own the foundational pipelines that transform messy documents, scanned records, and call transcripts into structured, reliable data for agentic AI systems. Working within a .Monks delivery team alongside clients, product partners, and domain experts, you’ll build extraction, classification, validation, and evaluation systems that downstream products can trust.
We’re all-in on agentic engineering. Tools such as Claude Code and Codex are part of our everyday workflow, and we’re looking for engineers who are fluent in working alongside AI coding agents and excited to advance these practices.
Responsibilities
Build extraction pipelines that transform documents, transcripts, and records into structured, schema-validated data
Combine LLMs with traditional parsing techniques, including OCR and layout analysis, to deliver reliable and cost-aware extraction
Design validation rules, confidence-scoring systems, and workflows that route low-confidence cases to human review
Build evaluation datasets and testing frameworks that measure extraction accuracy and identify regressions before release
Process diverse and degraded inputs, ranging from clean PDFs to poor-quality scans and inconsistent formats
Collaborate with clients, product teams, orchestration engineers, and domain experts to ensure clean data flows through the broader system
Communicate pipeline capabilities, limitations, quality thresholds, and risks clearly to technical and nontechnical stakeholders
Use AI coding agents, including Claude Code and Codex, as part of day-to-day engineering workflows
Other duties as assigned
About YouYou’re comfortable working with inconsistent formats, poor scans, and partially structured inputs. You approach extraction with precision, thinking carefully about edge cases, confidence thresholds, and validation. You understand the nondeterministic nature of LLM systems and know how to measure and improve their reliability.
Qualifications & Skills
5+ years of experience shipping production software
Hands-on experience extracting structured data from unstructured sources, including documents, transcripts, or records, using LLMs, classical NLP, and/or OCR
Experience with LLM structured outputs, tool calling, and prompt iteration
Experience developing in TypeScript and Node.js, or strong software engineering experience in another ecosystem such as Python
Familiarity with document AI tools and techniques, including OCR, layout parsing, Amazon Textract, Google Document AI, or similar platforms
Experience building and deploying solutions on AWS
An evaluation-driven approach to measuring quality, validating results, and iterating based on evidence
Strong understanding of edge cases, confidence scoring, schema validation, and nondeterministic systems
Professional English proficiency at B2 level or higher
Strong written and verbal communication skills, including the ability to explain system capabilities and limitations in plain language
Comfort working in a fast-paced, agile consulting environment
Experience using AI coding agents such as Claude Code or Codex
Experience delivering extraction systems in regulated or high-stakes industries such as legal, healthcare, or financial technology is a plus
Experience processing handwriting, multilingual documents, or heavily degraded scans is a plus
Experience building human-in-the-loop review tools for low-confidence outputs is a plus
A background in classical machine learning or NLP, experience with Writer.ai, or relevant open-source contributions is a plus
#LI-ML1 #LI-Remote