Helen Satchwell
Linguist. Systems Architect. Problem Solver.

​I grew up moving between Chile and the U.S. because of my parents' work in the mining industry. That experience of constantly navigating new environments and translating between cultures is what led me to study linguistics. Since then, my work has focused on making complicated systems actually make sense to people. I approach every project with a whiteboard mindset: I identify the logic gaps, strip away the jargon, and build the frameworks needed to ensure human-in-the-loop workflows remain accurate and consistent.

AI Integrity & Intent Evaluation 🤖​

I help to align human intent and machine logic.

I specialize in the "Human-in-the-loop" side of AI. From adversarial testing to PII filtering, I evaluate how models handle complex, multi-dimensional prompts. I don't just look for errors; I look for the patterns of failure to help engineers build safer, smarter systems.

Quality Architecture & Ops 📈​

Turning messy data into structured systems.
​
I thrive in "day zero" environments where there is no manual. I have a track record of walking into high-volume workflows, identifying the gaps in logic, and building the audit systems and Python-driven pipelines needed to scale quality from the ground up.​

Technical Enablement & Governance 🤝​

Translating the "Technical" into the "Actionable."

​Whether I’m training global vendor teams on AI safety or rewriting HOA bylaws to comply with state law, my goal is clarity. I strip away the ambiguity that causes inconsistent results, creating the documentation and training tools that allow teams to move fast without breaking things.​

Engineering a Standard from Scratch​

The Challenge: At AWS Bedrock, Task Leads and I were managing a 250,000-response AI dataset. Vendors performed 3-pass annotations across 9 independent dimensions, but there was no guidance on how to provide quality feedback. Without a framework, feedback was inconsistent, and our quality baseline scored 47%.

The "Whiteboard" Solution: I built the infrastructure that didn't exist.
  • The Audit Framework: I designed a mechanism to audit the feedback MLDLs were providing. I designed a QA feedback guide including examples, optional phrasing templates, and defining QA feedback scoring rubrics and expectations. I wrote Python scripts to automate the performance metrics and identify issues as soon as QA batches were processed.
  • Defining "Good" Feedback: I moved the team away from generic reviews. I established a requirement that every piece of feedback had to be a specific critique or structured praise, backed by a direct guideline citation.
  • Calibration & Coaching: I led the calibration sessions to ensure that 350+ people across global teams were finally speaking the same "quality language."

​The Result: By creating a clear standard where there was none, we moved the quality needle from 47% to 96.7% in a single quarter. We didn't just hit a target; we built a scalable, high-precision loop for GenAI training.
"Helen walks into a problem with a whiteboard in her head."
​
"She never just flagged issues; she’d come back with two or three solutions already mapped out, risks included. She's the person on your team who makes everyone around her better without making it a big deal."
​
​— Daisy Carlesso, Senior ML & GenAI Operations Manager, AWS
"A rare ability to build processes from the ground up."
​
"Helen’s most impactful contribution was designing a feedback mechanism from scratch that enabled highly precise quality feedback. She has a rare ability to create detailed procedures, identify gaps early, and iterate quickly until the process is robust enough to scale."
​
​— Mickael Dahlen, Data Operations Manager, AWS
​"Exceptionally reliable, meticulous, and deeply committed."
​
"Helen has a remarkable ability to translate complex processes into clear, well-structured documentation and operational guidelines. She led training sessions, mentored teammates, and helped colleagues build new capabilities."
​
​— Elvira Magomedova, ML Data Operations Manager

Real-World Systems: HOA Governance & Fiduciary Strategy​

Managing a 448-unit residential community is a lot like managing a global data team: it requires transparency, structured processes, and the ability to translate complex rules into something everyone understands.
As Board Secretary, I oversee a multimillion-dollar budget and manage the community's official records. I recently spearheaded a complete rewrite of our community regulations to remove legal ambiguity and ensure our rules were fair, enforceable, and aligned with state law. I treat community governance as a system that needs to be both robust and human-centric.

Languages & Technical Skills

Languages

  • English (Native)
  • Spanish (Fluent/Native)
  • Portugues (Intermediate)

Linguistic Data Science

  • LLM & RAG Evaluation
  • Adversarial Testing & Red-Teaming
  • Guardrails Analysis & Framework Design
  • Intent Recognition & Vendor Calibration

Analysis & Logic

  • Multi-dimension Evaluation Models
  • IAA Metrics (Cohen's Kappa, F1)
  • Statistical Significance Testing (p<0.05)
  • Sampling Methodologies
Tools & Platforms

  • AWS (S3, SageMaker) & SQL
  • JIRA & Wiki/Confluence
  • Appen & Advanced Excel

Python & NLP

  • Data Pipelines (JSON, CSV, TXT)
  • Pandas & NumPy
  • NLP Analysis (NLTK, spaCy)
  • statsmodels & sklearn

Technical Enablement

  • Technical Writing & SOP Development
  • Annotation Workflow Design
  • Data Transformation Scripting
  • Cross-functional Communication

Let’s Build Something Clear 🚀​

I’m currently looking for my next role in AI Operations, Learning & Development, or Technical Program Management. If your team is dealing with complex data, unstructured workflows, or a quality loop that needs a 'whiteboard' overhaul, I’d love to talk. I’m based in Boulder, CO, and am fully equipped for remote roles.

Find Me Here:
Site powered by Weebly. Managed by pair Domains