Forward Deployed Engineer · Los Angeles
From messy problems
to working products.
I take AI products from the first customer conversation to the last mile of production, and make sure they hold up in the real world.
- A vague askDiscover
- PeopleFrame
- Legacy toolsBuild
- Messy dataValidate
- UnknownsOperate
- Who owns it?Transfer
A little like my day job. Give it a click.
CommerceIQ · Data & infrastructure
Making the waiting disappear.
Both dots circle at the real ratio: one old run for every 480 new ones.
A media budget recommendation pipeline built on AWS Step Functions, SQS and Lambda with roughly 40 SQL modules. Same decision, a 480× shorter wait, and approximately $200K in annual client savings.
A way of working. Not a client blueprint.
Prentis AI · 2026–present
From possibility to product.
Building AI-powered products from discovery to production: customer conversations, product engineering, and the realities of getting software into use.
Ella · Knowledge systems
A better memory for the team.
A Slack assistant that finds answers in company knowledge, escalates what it can't answer, and turns those answers into knowledge the next person can use.
Also on my workbench.
Projects and early builds that shaped how I work.
How I work
Close to the problem.
All the way through.
The interesting part is connecting the pieces: what people need, what the model can do, and what the system must guarantee.
A vague ask
Talk to the people doing the work. Trace the workarounds. Find the problem beneath the feature request.
- 1
Understand the actual work.
Talk to the people doing it. Trace the workarounds. Find the problem beneath the request.
- 2
Use AI where it earns its place.
Models for ambiguity. Deterministic code for rules. Clear boundaries between the two.
- 3
Own the last mile.
Integration, evaluation, recovery and adoption. The job is done when the workflow actually works.
A little about me
Engineer by trade.
Curious by default.
I like problems that don't arrive neatly packaged. My foundation is in backend, data and distributed systems. At CommerceIQ I built pipelines, optimized infrastructure and grew into Forward Deployed Engineering. At Prentis AI I'm taking on the whole journey: discovery, product, engineering and production.
I completed my M.S. in Computer Science at CSULB in May 2026. Outside the implementation details, I'm drawn to philosophy, psychology and how people think, and there's usually a good film somewhere in the mix.
The journey so far
Built on experience.
Still asking questions.
- Jun 2026 – now
Prentis AI Forward Deployed Engineer
Sole engineer on a HIPAA/PHI claims-automation deployment for a major California healthcare payer, from discovery to a live parallel run in six weeks. A Claude on Amazon Bedrock pipeline replaced an offshore data-entry vendor, with a golden-set eval harness gating every change: 96% field-level accuracy, within 2 points of the human vendor on production traffic.
- Feb – May 2026
CommerceIQ Forward Deployed Engineer
Owned three brand deployments, Meta, Hill's Pet Nutrition and SharkNinja, from Day 1 discovery to Day 60 production sign-off, on a multi-tenant analytics portal I built underneath them. For Meta, a Difference-in-Differences model put retail-media lift at about +5 pp. Productionized Ally, GPT-4o executive summaries with guardrails.
- May – Jul 2025
Stealth startup Full Stack Engineer
Benchmarked Text-to-SQL across LLaMA, OpenAI and Gemini for quality, latency and cost, with timeouts, fallbacks and caching. Built personalization workflows on semantic embeddings and raised query throughput 85%.
- Sep 2021 – Aug 2024
CommerceIQ Software Engineer · SDE 1 → SDE 2
Built an AWS media-budget recommendation pipeline that cut processing from 1 day to 3 minutes and saved clients $200K a year. Solved cold start with synthetic data, moved budget prediction from Snowflake to Databricks (infra cost −52%, latency −80%), and automated Amazon Advertising and Criteo campaigns, cutting manual operations 60%.
Education
California State University, Long Beach
M.S. Computer Science · May 2026 · GPA 3.9 / 4.0
Graduate Teaching Assistant (AI), Instructional Assistant (Ethical & Explainable AI) and Research Assistant (Neuromarketing & AI). Tau Beta Pi, CA Theta.
Education
Ramaiah Institute of Technology
B.E. Information Science & Engineering · 2017–2021 · GPA 8.52 / 10
Applied AI
Claude on Amazon Bedrock, GPT-4o, Gemini, LangGraph and MCP. Document extraction, RAG with hybrid retrieval, Text-to-SQL, golden-set evals and human-in-the-loop review.
Backend & data
Python (FastAPI, SQLAlchemy, asyncio), SQL, Java and JavaScript. PostgreSQL, SQL Server, Snowflake, Databricks, PySpark and Airflow.
Cloud & delivery
AWS (Bedrock, ECS Fargate, Lambda, Step Functions, S3, SQS), Terraform, Docker and GitHub Actions. HIPAA/BAA review, pilots, parallel runs and handoff runbooks.
Certifications
Forward Deployed Engineer for AI Systems · Claude Code in Action · Mastering MCP · AI Engineer Agentic Track · GCP Fundamentals · Responsible AI Data Management
A competitive streak
A deadline. A team.
A working idea.
- Winner
Smart India Hackathon
Police Beats Allocation for the National Crime Records Bureau.
- Runner-up
Microsoft IncubateIND
Women Suraksha: maps and emergency alerts connecting people with help.
- Honorable mention
CommerceIQ AI Hackathon
Language models for review sentiment and competitor comparison.
- Runner-up
GE Healthcare Precision
Hospital workflows and waiting times.
- Runner-up
Reverie Language Hackathon
Translation and multilingual communication.
- Runner-up
IEEE Ideathon
An early practice run at the full loop.
Thinking out loud
A few ideas outside the code.
Let's make it work.
An ambiguous problem, a product to build, or a good conversation. I'm based in Los Angeles.