Barbara Hidalgo-Sotelo, PhD, CDMP

Lead Analyst • Evaluation & Experimentation • Data Science (Python/SQL) • Metrics & Data Pipelines

Austin, TX (remote/hybrid) • (512) 804-9995 • barbs@balex.combarbhs.comgithub.com/dagny099 • US Citizen

SUMMARY

Lead analyst and data scientist with 6+ years owning end-to-end analytics and ML delivery in consulting and stakeholder-heavy environments—from requirements and stakeholder alignment, to data readiness (SQL/ETL, quality checks), to modeling/evaluation and repeatable analysis pipelines. Strong foundation in statistical reasoning and experiment design (hypothesis testing, A/B testing), with a track record translating complex findings into clear, defensible decisions. Advanced Python and SQL; cloud experience across Azure/AWS/GCP; pragmatic strengths in documentation, version control, and reliable handoff.

CORE STRENGTHS

PROFESSIONAL EXPERIENCE

Independent AI Engineering (Project-Based)Self-directed
May 2025–Present • Remote
  • Built evaluation-minded GenAI retrieval workflows (RAG/GraphRAG patterns), emphasizing traceability (citations/provenance) and repeatable runs.
  • Designed modular pipelines with clear interfaces (ingestion → retrieval → generation → evaluation) to support iterative testing and future productionization.
Technical Consultant (Program Delivery / Change Management)Inflective, Inc.
Jan 2024–May 2025 • Remote
  • Partnered with stakeholders to assess program status, risks, and quality; translated findings into clear actions to keep cross-functional delivery on track.
  • Resolved delivery blockers across business and technical teams, improving execution reliability and reducing friction for multi-workstream programs.
Data Scientist (Federal client: financial markets & data governance)Metric5 Consulting
Apr 2021–Jan 2023 • Remote
  • Built Python tooling to streamline metadata export and reporting workflows in a standards-driven environment; authored documentation to support adoption.
  • Developed a proof-of-concept reporting utility integrating ServiceNow and enterprise data catalog tooling to improve handling of data access requests.
  • Collaborated with engineers and analysts to assemble datasets and deliver repeatable reporting, emphasizing data validation and reliability.
Technical Consultant & Project Manager (Healthcare analytics / risk management)Inflective, Inc.
Aug 2017–May 2019 • Remote
  • Led a digital transformation initiative optimizing adjudication and analytics workflows, achieving ~30% faster processing time and meaningful cost savings.
  • Designed and implemented a Python/scikit-learn classification model to automate medical bill categorization with performance comparable to human coders.
  • Co-led process workshops to reduce error rates by ~25%; delivered in Agile (Jira) and presented results to executive stakeholders.

SELECTED ANALYTICS & EVALUATION HIGHLIGHTS

Note: domain experience is cross-industry; prepared to ramp quickly in safety-critical evaluation contexts using rigorous measurement and reproducible methods.

EARLIER EXPERIENCE

Co-Founder & Technical LeadBALEX Healthcare Services (co-founded; owned EMR/billing workflow architecture and delivery)
2015–2017 • Austin, TX
  • Led end-to-end delivery of EMR/billing workflow solutions—from requirements and process mapping to prototype, UAT, and rollout in resource-constrained settings.
  • Identified gaps across clinical, billing, and audit workflows; translated stakeholder needs into technical requirements and systems integration plans.
Technical Consultant (Requirements, QA/QC, Enablement)Persis Consulting
2014–2017 • Remote
  • Documented software requirements and supported Agile delivery; managed QA/QC and produced end-user training materials to improve adoption.
Research Engineer/ScientistThe University of Texas at Austin
2013–2016 • Austin, TX
  • Engineered secure data collection and automated analysis workflows (Python/MATLAB); supervised lab staff and undergraduate research assistants.
Research Project Manager (Biometrics & marketing effectiveness)MediaScience
2017 • Austin, TX
  • Executed hypothesis-driven analyses on multimodal biometric data to quantify engagement; delivered client-ready reporting and recommendations.

TECHNICAL SKILLS

Languages: Python; SQL (PostgreSQL/MySQL/BigQuery); R; MATLAB; Bash
Analytics & Statistics: experimental design; hypothesis testing; regression/classification; uncertainty-aware reporting; data visualization (Plotly/Matplotlib)
Data Engineering: ETL/ELT pipelines; data cleaning; validation/quality checks; metadata management; reproducible ingestion workflows
ML Tooling: scikit-learn; pandas/NumPy; feature engineering; model evaluation & error analysis
GenAI (selected): LlamaIndex; LangChain; embeddings & retrieval; RAG/GraphRAG-style workflows; evaluation-minded iteration
Datastores: PostgreSQL/MySQL; Neo4j (Aura); basic familiarity with document stores
Cloud & Apps: Azure; AWS (EC2/RDS/Lambda); GCP (BigQuery); FastAPI/Flask; Streamlit
Collaboration: Git/GitHub; documentation; automated testing; CI/CD exposure; Agile (Jira)

EDUCATION

CERTIFICATIONS