I'm excited to launch this blog as a space to document my journey through Computer Science at Arizona State University. After 10 years at Intel, first as a Process Engineer and then as a Software Application Engineer, I'm finishing up my last 2 semesters of my Master's in Computer Science while exploring the cutting edge of AI and data science.
Why Start a Blog?
Throughout my career transition from semiconductor manufacturing to software engineering, I've learned that documenting your journey serves multiple purposes:
- Reinforces learning - Writing about concepts forces you to truly understand them
- Creates a portfolio - Future employers can see your thought process and growth
- Helps others - Someone on a similar path might benefit from your experiences
- Tracks progress - It's motivating to look back and see how far you've come
What to Expect
I plan to cover a variety of topics related to my studies and projects:
Coursework Insights
Sharing key takeaways from courses like Statistical Machine Learning, Agentic AI, Data Processing at Scale, and Advanced Operating Systems. Not just summaries, but practical applications and "aha!" moments.
Project Deep Dives
Technical walkthroughs of projects I'm building—from MultiAgent-Pipeline to experiments with local LLMs on the ASU Sol supercomputer. Here's a taste of what a code snippet might look like:
from solvers.openai_solver import OpenAISolver
from solvers.anthropic_solver import AnthropicSolver
# Dual-model consensus: GPT and Claude solve, then compare
async def run_consensus(problem_path: str):
openai_solver = OpenAISolver()
anthropic_solver = AnthropicSolver()
# Both models solve in parallel
response_a, response_b = await asyncio.gather(
openai_solver.solve(problem_text, references_text),
anthropic_solver.solve(problem_text, references_text)
)
# Compare and iterate until 90%+ agreement
comparison = compare_answers(response_a, response_b)
return comparison.agreement_percentageIndustry + Academia
Reflections on bridging the gap between industry experience and academic research. In this section, I explore how real engineering challenges at Intel connect to concepts I'm learning in grad school. From solving performance problems to building reliable systems, I'm documenting how my industry background helps me understand theory faster, and how academic knowledge makes me a better engineer.
Tools & Tips
Leveraging Claude Code and API integrations to streamline my development workflow while deepening my understanding of AI systems. From automating tedious tasks to building intelligent pipelines, I'm documenting how modern AI tools can amplify productivity without replacing the learning process.
Let's Connect
I'd love to hear from you! Whether you're a fellow student, a recruiter interested in my work, or someone on a similar career transition path—feel free to reach out via LinkedIn or email.
Stay tuned for more posts, and thanks for being here at the very beginning of this journey! 🚀