Portfolio — 2026

Abhishek
Tuteja

Open to Work

SAP Functional Analyst · Commodity Trading & Risk

I keep the numbers behind commodity trading honest. Ex-Deloitte, now building data and AI tools for finance.

About

I specialize in the SAP systems behind commodity trading and risk, the kind of work where a single wrong number costs real money. At Deloitte I spent two years on a Fortune 100 agricultural commodities trader's platform, owning the daily mark-to-market risk report, reconciling multi-commodity positions across SAP ACM and BW, and driving daily open issues to near zero.

That work went well beyond day-to-day operations. I led end-of-day reporting for a three-analyst Center of Excellence, supported S/4HANA rollouts across LATAM, EMEA, and APAC, and ran a risk and controls review on an SAP Signavio ERP transformation, owning the SOX and Non-SOX control matrix all the way through stakeholder sign-off.

A Computer Science master's from Northeastern (3.96 GPA) sharpened the technical half of that equation. I now build data and AI tools for finance, including PROVA, a multi-agent system that scores model risk documentation against SR 11-7, and CapTrack, a trade analytics platform with deterministic, multi-currency P&L. Domain depth on one side, engineering on the other.

Languages

PythonSQLTypeScriptJavaVBA

ML & AI

Multi-Agent OrchestrationLLM Prompt EngineeringRAG Pipelinesscikit-learnXGBoostRandom Forest

SAP & Enterprise

SAP S/4HANASAP ACMSAP BWSAP SignavioSOX ControlsRisk & Control Matrix (RCM)UAT

Tools

GitPostgreSQLMySQLMongoDBSupabaseJupytermatplotlibPower BIExcel

Experience

01Jan 2025 - Apr 2026

Teaching Assistant

Northeastern University — Oakland, CA

Teaching assistant for three core Computer Science courses: Introduction to Programming (CS 2000, Python and Pyret), Object-Oriented Design in Java (CS 3100), and Database Design (CS 3200).
Led graded code-walk reviews, assessed assignments, and held office hours, coaching students through programming, object-oriented design, and relational modeling.

02May 2022 - July 2024

Advisory Analyst

Deloitte — Bengaluru, IN

Owned the daily Stock Mark-to-Market risk report for a Fortune 100 agricultural commodities client, reconciling multi-commodity positions across SAP ACM and BW and validating long and short P&L and landed cost over thousands of records every day.
Drove daily open issues to near zero, investigating transaction breaks across the contract, load-capture, and settlement chain, reproducing defects in DEV, scoping fixes for ABAP developers, and validating through UAT.
Led end-of-day reporting for a three-analyst Center of Excellence and rolled out SAP ACM across LATAM, EMEA, and APAC, handling configuration localization and knowledge transfer. Deloitte Spot Award recipient.
Ran a risk and controls review on an SAP Signavio ERP transformation for a US oil and gas client, owning the SOX and Non-SOX Risk and Control Matrix (RCM) from process mapping through stakeholder sign-off.

03Oct 2020 - Nov 2020

Machine Learning Intern

Steinn Labs — Remote

Built an OCR pipeline in Python and TensorFlow that pulled structured data from scanned identity documents for database integration.
Lifted extraction accuracy by roughly 15% through preprocessing, model tuning, and validation against labeled samples.

Education

Master of Science in Computer Science

Sept 2024 - May 2026

Northeastern University — Oakland, CA

GPA: 3.96

Algorithms, Database Management Systems, Programming Design Paradigm, Foundations of AI, Foundations of Software Engineering, Machine Learning, Generative AI, AI-Assisted Development

Bachelor of Technology in Mechanical Engineering (Minor: Data Science)

July 2018 - July 2022

Manipal Institute of Technology — Manipal, KA

GPA: 3.71

Projects

What I've been building.

Prova

Upload model risk documentation, get an SR 11-7 compliance score and gap analysis in minutes.

Three parallel AI agents assess model documentation against all three validation pillars, Conceptual Soundness, Outcomes Analysis, and Ongoing Monitoring, across 20 regulatory elements. A judge and orchestrator layer checks the agents against each other, with automatic retry and scoped re-assessment for disputed findings. The output is a weighted compliance score, a per-element gap analysis with evidence citations, remediation recommendations, and a downloadable PDF report.

Next.jsTypeScriptSupabaseAnthropic API

CapTrack

Trade and portfolio analytics that get P&L right under messy, real trading conditions.

Ingests broker trade data, normalizes it into a consistent schema, and constructs positions with accurate realized and unrealized P&L. Built to handle the cases that break naive trackers: partial fills, multiple trades per asset, short positions, and multi-currency reconciliation. The priority is deterministic, auditable accounting over flashy visualization.

Next.jsTypeScriptSupabasePostgreSQL

View all on GitHub →

My Two Cents

Notes on building, breaking, and figuring things out.

Apr 22, 20266 min read

Why Our AI Agents Kept Lying About Their Scores

We built an app where three AI agents assess banking documents for regulatory compliance. Then we discovered they couldn’t do basic arithmetic. This is the…

model-validationmulti-agent-systems

Read article →

Mar 13, 20266 min read

Most Habit Apps Punish You for Missing a Day. Forge Doesn’t.

Instead of punishing missed days, Forge helps you understand your patterns, design momentum, and build identity through habits.Most habit apps make one…

technologyself-helphabitsatomic-habit

Read article →

View all on Medium →