Senior Artificial Intelligence/Machine Learning Engineer

The Senior Artificial Intelligence/Machine Learning Engineer will design and deliver production-grade AI systems that transform complex, unstructured documents into accurate, structured data. This hands-on engineering role focuses on agentic AI, document intelligence, large language models (LLMs), and retrieval-augmented generation (RAG) within scalable AWS environments. You will build intelligent extraction agents, resilient document ingestion pipelines, and confidence-based routing systems that balance automation with human oversight. The role emphasizes reliable outputs, secure domain-specific knowledge, measurable model performance, and responsible AI governance. You will also optimize inference costs and latency while developing evaluation frameworks and feedback loops that continuously improve system quality. Working within a collaborative, cross-functional engineering team, you will mentor other engineers and help establish reusable technical patterns for dependable, high-impact AI solutions.

• Deep experience in AWS architecture, including hands-on work with Amazon Bedrock in production environments.

• Strong expertise in model selection, prompt engineering, context engineering, model evaluation, and optimizing inference costs and latency.

• Substantial experience with document AI and optical character recognition (OCR), including processing degraded inputs using Amazon Textract or equivalent technologies.

• Strong understanding of layout-aware extraction and the challenges of transforming OCR output into reliable, schema-compliant structured data.

• Demonstrated experience extracting structured information from long, unstructured documents into fixed schemas, including field-level confidence estimation and calibration.

• Proven ability to build agentic AI systems involving multi-step reasoning, tool-use protocols, and state management for autonomous agents.

• Production experience building RAG or LLM pipelines, including document chunking, retrieval strategies, contextual grounding, and knowledge integration.

• Experience designing human-in-the-loop systems that route uncertain model outputs for review rather than relying on unverified automated decisions.

• Ability to incorporate reviewer corrections into feedback loops that support continuous model and system improvement.

• Strong end-to-end ownership, including responsibility for ingestion, inference, evaluation frameworks, monitoring, and production feedback mechanisms.

• Desirable experience: Familiarity with selective prediction and confidence calibration techniques, including determining when a model should abstain because it lacks sufficient confidence.

• Desirable experience: Building programmatic evaluation frameworks and testing against curated reference datasets to measure field-level accuracy, review-queue precision and recall, and model drift.

• Desirable experience: Working with proprietary domain-specific datasets and developing data governance practices for specialized knowledge sources.

• Strong problem-solving, communication, and collaboration skills, with the ability to guide other engineers and establish effective engineering practices.