(510)407-2646
EILEEN BLUM
PhD
(510)407-2646 eileen.blum92@gmail.com
ABOUT ME
I am an experienced technical writer specializing in conversational AI. I like to describe my work as translating 'software engineer' for the general public. Through documentation, I ensure that anyone can understand and implement Google Cloud's customer engagement suite products and features.
I write public-facing knowledge bases, including conceptual documents, setup and troubleshooting guides, and best practices. I've also written client-specific recommendations for using DialogflowCX, and task instructions for training new employees. I love when something I have written can directly help others to accomplish their technical goals.
Outside of work, I love spending time with animals. I rode and trained off-the-track thoroughbreds in the hunter/jumper discipline for over ten years and now I volunteer at a local adaptive riding program. I trained my first dog as a kid and even trained my late cat to perform some basic tasks on cue.
WORK EXPERIENCE
February 2024 - Present
TECHNICAL WRITER, Data Piper
Google Customer Engagement Suite – Agent Assist and Insights
Deliverables:
-
Implement new information architecture schema: reorganize documentation sites to improve searchability
-
Create, update, and maintain API documentation and release notes for all new AI-driven features that help contact centers process and analyze up to 20 million voice calls
-
Plan, design, write, and update over 40 public documents, including REST/JSON APIs, CLIs, SDKs, concepts, and how-to guides
-
Adhere to Google quality standards and style guides to ensure everyone can access and understand content
Tools:​
-
Write for the web with Markdown, HTML, and XML for online publication
-
Utilize single sourcing and change management techniques, such as static and
dynamic includes and version control -
Create, manage, and submit changes using Cider-V and Critique
Collaboration:
-
Train five new employees to build a technical writing team
-
Collaborate with product managers, engineers, and UX team to ensure technical
accuracy and address user needs in documentation -
Consult with peers, senior writers, and editor to ensure consistency and quality of documentation
-
Work with functional partners to manage and prioritize the technical writing workload
September 2022 - February 2024
DIALOGUE DESIGNER, Data Piper
Google Customer Engagement Suite – Agent Assist
Deliverables:
-
Edited 4 Agent Assist documents for clarity and comprehension in English
-
Wrote client-facing DialogflowCX recommendations to improve call containment up to 185%
-
Wrote instructions and sample data for 90 conversations to train an Agent Assist LLM
-
Annotated and summarized 557 customer service conversations over 6 months for 5 clients
-
Wrote instructions and sample data for 90 conversations to train an Agent Assist LLM
Collaboration:​
-
Reviewed existing documentation and participated in peer reviews to improve clarity and accuracy of content
July 2021 - July 2022
DIALOGUE DESIGNER, Tek Systems
Google Customer Engagement Suite –Virtual Agent
Deliverables:
-
Designed, co-wrote, and edited best practices for Dialogflow CX
-
Wrote documentation guide and edited ReadMe for SCRAPI Python library on Github
-
Wrote 17 instructional documents to clarify processes and train 5 new team members
-
Annotated conversation data to identify virtual agent failures and successes
-
Able to prioritize and work under pressure and with tight deadlines in an agile workflow
Tools:​
-
Maintained and improved virtual agent using Dialogflow CX
-
Edited SCRAPI documentation hosted on Github using Gitlab
PROJECTS
PhD DISSERTATION
The effects of non-linear data structures on the computation of vowel harmony (Jan 2023)
I apply formal language theory to natural language data in order to analyze the computational complexity of vowel harmony patterns across both well studied and understudied languages. I use this computational approach to investigate the effects of different representational data structures on complexity and I develop a new theory of autosegmental locality.
METAL LYRICS GENERATOR
Erdös Institute Natural Language Processing Bootcamp (February-March, 2021)
My partner and I built a Wasserstein Generative Adversarial Network (WGAN) in Python to generate automated song lyrics in lines of 8 words at a time. We compared our WGAN with a Soft-GAN trained on the same dataset. We trained both GANs on a Kaggle dataset of metal song lyrics, which we processed using NLTK and pandas. The GANs were built using Keras, Tensorflow, and Numpy. Lastly, we calculated BLEU scores for both models and determined that neither generated very natural sounding lyrics: WGAN received all 0s, Soft-GAN averaged 0.06 for n-grams of length 1-4.
METAL OR NOT?
Erdös Institute Data Science Bootcamp (May 2020)
My partner and I created a classifier in Python to distinguish song lyrics by genre. We used two Kaggle data sets of song lyrics which were cleaned using the GenSim and NLTK packages. We then used the shallow neural network in the Word2Vec package to create high-dimensional word vectors, PCA and k-clustering to group them based on semantic similarity, and trained a DecisionTreeClassifier to distinguish lyric sets. The classifier achieved 81% accuracy.
QUALIFYING PAPER 2
On the locality of vowel harmony over autosegmental representations (2018)
I applied Formal Language Theory to natural language data in order to analyze the computational complexity of vowel harmony patterns over autosegmental representations. I analyzed vowel harmony patterns in multiple languages and predicted possible cross-linguistic variation.
QUALIFYING PAPER 1
Allophony-driven stress in Munster Irish (2018)
I designed and implemented a production experiment to determine the word stress pattern of Munster Irish (Gaelic). I organized all the data files by hand in Excel, then annotated, transcribed, and analyzed all of the acoustic data by hand in Praat. Statistic analyses was performed using t-tests in Excel then verified using linear mixed effects models in R.