Ian A.

Key Skills

Software

Snorkel AI

Top Subject Matter

LLM evaluation/benchmarking and verification

LLM application development and controlled text generation

Top Data Types

Image

Top Task Types

Prompt + Response Writing (SFT)

Freelancer Overview

AI Expert Contributor (DevOps) at Snorkel AI (benchmarking and evaluation). Brings 3+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Snorkel AI and OpenAI API. Education includes Bachelor of Science, Arizona State University (2026). AI-training focus includes data types such as Computer Code and Programming and labeling workflows including Evaluation, Rating, and Prompt + Response Writing (SFT).

Labeling Experience

AI Expert Contributor (DevOps) at Snorkel AI (benchmarking and evaluation)

Snorkel AI

Contributed to Snorkel AI as an AI Expert Contributor (DevOps) by building and verifying software engineering benchmarks to stress-test frontier large language models. Focused on deterministic evaluation, reproducibility, and exhaustive coverage of technical edge cases during benchmark automation and validation. Investigated model failure modes and performance metrics to iteratively improve verification rigor and evaluation frameworks. • Engineered benchmark pipelines using Python and system architectures to evaluate LLM behavior • Created automated validation suites emphasizing determinism and reproducibility • Analyzed LLM failure modes and performance metrics to strengthen evaluation coverage • Supported verification and benchmarking infrastructure as part of DevOps work for AI models

2026 - Present

Full-Stack Engineer at Noema (AI-powered journaling platform)

Prompt + Response Writing (SFT)

Built an AI-powered journaling platform by integrating OpenAI GPT-4o-mini to generate personalized AI reflections. Designed structured safety gating and user preference controls to govern generated outputs. Implemented local-first preference storage and scalable cloud architecture to support reliable, privacy-focused AI generation. • Developed backend API routes for GPT-4o-mini-driven journaling reflections • Implemented safety gating and preference-based controls for generation • Designed local-first storage for user preferences and scalable deployment using Supabase/Vercel • Delivered end-to-end platform functionality using modern web and API tooling

2025 - Present

Education

Work History