Ishank Sharma Get in touch

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.

See my work Résumé
  • Applied AI
  • Backend systems
  • 0-to-1 ownership
  • 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.

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.

Has anyone solved this before?

Let’s start with what
your team already knows.

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.

Everything on GitHub

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. 1

    Understand the actual work.

    Talk to the people doing it. Trace the workarounds. Find the problem beneath the request.

  2. 2

    Use AI where it earns its place.

    Models for ambiguity. Deterministic code for rules. Clear boundaries between the two.

  3. 3

    Own the last mile.

    Integration, evaluation, recovery and adoption. The job is done when the workflow actually works.

Portrait of Ishank Sharma

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.

LinkedIn GitHub

The journey so far

Built on experience.
Still asking questions.

Education

California State University, Long Beach

M.S. Computer Science · 2024–2026 · GPA 3.9 / 4.0

Education

Ramaiah Institute of Technology

B.E. Information Science & Engineering · 2017–2021 · Bengaluru

Applied AI

Claude, Amazon Bedrock, GPT, RAG, embeddings, Text-to-SQL, evaluation and human-in-the-loop workflows.

Backend & data

Python, Java, SQL, JavaScript, FastAPI, Flask, PostgreSQL, SQL Server, Snowflake and Databricks.

Cloud & delivery

AWS, Docker, Step Functions, SQS, Lambda, CI/CD, observability, and systems that recover when things go wrong.

A competitive streak

A deadline. A team.
A working idea.

Thinking out loud

A few ideas outside the code.

More on Medium

Let's make it work.

An ambiguous problem, a product to build, or a good conversation. I'm based in Los Angeles.

ishankdev@gmail.com LinkedIn GitHub