Forward Deployed Engineer
Los Angeles, California
I’m Ishank. I turn ambiguous problems into AI products that work in the real world. From the first customer conversation to the last mile of production.
Explore my workA little like my day job. Give it a click.
Customer context meets engineering depth.
Useful software starts with a real problem.
Here are a few of mine.
CommerceIQ / Data & infrastructure
A media budget recommendation pipeline built with AWS and roughly 40 SQL modules. Processing fell from a day to about three minutes, with approximately $200K in annual client savings.
Step Functions, SQS, Lambda, SQL
A way of working. Not a client blueprint.
Prentis AI / 2026–present
Forward Deployed Engineer, building AI-powered products from discovery to production.
Let’s start with what
your team already knows.
Ella / Knowledge systems
A Slack assistant that finds answers in company knowledge, escalates unanswered questions, and turns those answers into knowledge the next person can use.
View my GitHubProjects, experiments, and a few early builds that shaped how I work today.
5 projects in the collection
Semantic document search with a visual view of the embeddings behind the answers.
LangChain · ChromaDB · Gradio · t-SNE
Custom neural networks, optimizer experiments, and image classification on CIFAR-100. Built while studying the fundamentals.
PyTorch · NumPy · CNNs · MLPs
Exploring millions of accident records through maps, clusters, heatmaps, and interactive filters.
Firebolt · Flask · Mapbox · Python
A lightweight API prototyping server with CRUD operations, filtering, search, and JSON persistence.
Node.js · Express · REST
A Smart India Hackathon-winning project for police operations, with officer tracking, zones, and alerts.
Django REST · Mapbox · Firebase
The interesting part is connecting the pieces: what people need, what the model can do, and what the system must guarantee.
Talk to the people doing it. Trace the workarounds. Find the problem beneath the feature request.
Models for ambiguity. Deterministic code for rules. Clear boundaries between the two.
Integration, evaluation, recovery, and adoption. The job is done when the workflow actually works.
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. These days, I’m based in Los Angeles, working at the intersection of customer context and applied AI.
Outside the implementation details, I’m drawn to philosophy, psychology, and questions about how people think. There’s usually a good film somewhere in the mix, too.
From backend and data foundations to owning the whole path from customer problem to working product.
Building AI-powered products from discovery to production. Working across customer discovery, product engineering, and the realities of getting software into use.
Built multi-tenant analytics experiences for executive teams, bringing together dashboards, causal analysis, and AI-generated insights.
Productionized Ally, an executive-summary system using GPT-4o with structured prompts and guardrails.
Supported labs, grading, and student learning around model interpretability and responsible AI.
Built across a 0-to-1 product, including Text-to-SQL, semantic search, and LLM inference. Compared model quality, latency, and cost; added caching, fallbacks, and regression tests.
Explored webcam-based gaze tracking and advertising effectiveness, including calibration, gaze heatmaps, visual attention, and saliency research.
Built backend, data, and advertising systems. A media-budget pipeline reduced processing from roughly a day to three minutes and delivered approximately $200K in annual client savings.
Worked on cold-start recommendations, the migration of budget-prediction workloads from Snowflake to Databricks, Amazon Advertising systems, and Criteo strategy automation.
Investigated Snowflake multi-cluster concurrency and built monitoring dashboards to understand performance and tail latency.
M.S. Computer Science · 2024–2026
Completed May 2026 · GPA 3.9 / 4.0
B.E. Information Science & Engineering
2017–2021 · Bengaluru, India
Claude, Amazon Bedrock, GPT, RAG, embeddings, Text-to-SQL, evaluation, and human-in-the-loop workflows.
Python, Java, SQL, JavaScript, FastAPI, Flask, PostgreSQL, SQL Server, Snowflake, and Databricks.
AWS, Docker, Step Functions, SQS, Lambda, CI/CD, observability, and systems that recover when things go wrong.
Hackathons were an early way to practice the full loop: find a useful problem, build something real, and explain why it matters.
Winner · Team Avocado
Police Beats Allocation: tools for digitizing police operations, built for the National Crime Records Bureau.
Runner-up
Women Suraksha, using maps and emergency alerts to connect people with help.
Honorable mention
Using language models to understand product-review sentiment and compare competitors.
Honorable mention
A project focused on hospital workflows and waiting times.
Runner-up
Exploring translation and multilingual communication.
Runner-up
From data visualization to the fourth dimension. A few pieces from my earlier writing, and the questions I was working through.
More on Medium