graph by datavruti
mygraph.id/mayawhitfield96

Maya Whitfield

AI Engineer

Berlin, GermanyBuilding since Jul 2021 (5+ yrs)
LinkedInGitHub
Headline

My career shows a clear arc from ETL and churn modeling into owning task success rate, hallucination rate, latency, and cost as core metrics for a live LLM system. That combination of measurement rigor and production ownership is distinctive.

93%Task Success Rate

(up from 71%)

3%Hallucination / Faithfulness Rate

(down from 17%)

890ms p95 (down from 3.4s)Latency
$0.0074/request (down 61% from $0.019)Cost per Request
Represented Roles

Specialized Functions & Roles.

Engineering capabilities and specialized roles demonstrated across real production work.

AI Engineer

Primary Role

Machine Learning Engineer

LLM Systems Engineer

MLOps Engineer

Signals

Live in Production.

Each signal ties back to a specific, evidenced moment.

Built

3 moments

Systems shipped end-to-end, from schema to deploy.

  • •Shipped v2 of the RAG evaluation harness, added a hallucination-detection metric, picked up by 4th team
  • •Shipped the team's first automated LLM eval pipeline
  • •Open-sourced a RAG evaluation harness adopted by 3 teams

Solved

3 moments

Gaps closed - false positives, edge cases, dead ends.

  • •Raised task success rate from 71% to 93% on a production LLM assistant
  • •Cut hallucination errors from 17% to 3%
  • •Cut cost per request by 61%, saving ~$46K/year

Learned

1 moment

New tools and depth picked up on the job.

  • •Experimenting with agentic AI
Growth trajectory

Maya's career, mapped.

A timeline of milestones captured directly from real work.

  1. Started shipping production ML pipelines

  2. Standardized deployment across global offices

  3. Shifted focus to production LLM systems

  4. Built the team's first LLM evaluation pipeline

  5. Drove major reliability and cost wins

  6. Started sharing expertise publicly

Stack

Daily tools.

What Maya actually reaches for, pulled from the tags attached to captured moments.

Work

Key Projects By Role

Case studies, not bullet points - impact numbers attached to each one.

Lumen Cognitive

Senior AI Engineer · Mar 2023 - Present

Northfield Analytics

Machine Learning Engineer · Jul 2021 - Feb 2023
Outside Work

Side projects, open source & publications.

Independent builds, open-source contributions, technical writing, and experiments beyond the day job.

Experiment

Agentic AI Exploration

Currently experimenting with agentic AI approaches.

Present
Side project

Support Ticket Triage Classifier

Built and shipped a fine-tuned classifier that auto-routes incoming support tickets to the correct specialist queue, cutting manual triage time by 70%.

Side project

RAG Evaluation Harness

Built and open-sourced a Python library for automated RAG pipeline evaluation (retrieval precision/recall, answer faithfulness, latency benchmarking); adopted by 3 other internal teams and starred 400+ times on GitHub.

Side project

Customer Segmentation Engine

Built an unsupervised clustering pipeline to segment customers for the marketing team, used to drive quarterly campaign targeting.

Side project

Internal Document Q&A Assistant

Built a retrieval-augmented generation system over internal engineering documentation using LangChain and a vector database, held to a 90%+ task success rate on a 200-question eval set before rollout, reducing time spent searching internal docs across a globally distributed engineering team.

Learning

Formal record.

  • AWS Certified Machine Learning - Specialty
    AWS
    2023
  • B.Sc. in Computer Science
    University of Toronto
    2021
Activity heatmap

A record of momentum.

A combined view of Maya's activity across the tools used daily.

LessMore

Profile last updated 2 days ago.

Liked Maya's graph?

Build yours today.

Start with your resume