Alfred Churchill

Experience

• 

  Leoforce

  Nov 2021 - Aug 2023

  Software Test Engineer

  1.Execute validation tests on LLM models to evaluate chat bot responses and English language generation quality.2.Validate machine learning prediction endpoints and ensure alignment with ground truth data.3.Develop and execute validation test cases to assess the performance and correctness of LLM models.4.Good understanding of probability and statistics and their applications to AI/ML software quality evaluation5.Familiarity with statistical analysis techniques and machine learning algorithms6.Familiarity with AI/ML modeling approaches such as supervised and unsupervised techniques Show less

• 

  FHPL - Family Health Plan Insurance TPA Limited

  Aug 2023 - now

  QA Engineer (AI/ML)

  Machine Learning Models QA/Validation SME➡️ Supported data science team in ensuring the quality and validity of machine learning models.Collaborated with data scientists and project teams to document Model Qualification Plans and Technical Specifications.➡️ Defined business and technical requirements for ML models, including accuracy, performance, and functionality.➡️ Created, reviewed, and approved test cases to validate model adherence to requirements and performance criteria. Partnered with data scientists and subject matter experts (SMEs) to conduct thorough model evaluations and testing.➡️ Generated summary reports summarizing test results and model performance according to qualification plans.➡️ Analyzed test results and provided constructive feedback for model improvement. Show less

• 

  Unremot (Techstars '21)

  Sept 2024 - now

  Prompt Engineer