$ init utkarsh.saraogi --target=portfolio
[ ok ] mounting /skills 35 tools · 4 areas
[ ok ] connecting github://utkarsh1610-s 6 repos
[ ok ] warming stream.console subscribed → 6 topics
[ ok ] ready. press / to query.
LIVE
/
utkarsh.saraogi
/
Boston, MA
/
—
open to full-time · May 2027
query /
open to May 2027 full-time roles
Utkarsh Saraogi

Utkarsh
Saraogi.

Data Engineer
pipelines · streaming · warehousing
ML / AI Engineer
models · LLM evaluation · interpretability

Three years at HPE taught me that data systems don't fail because of bad ideas — they fail because of bad data. That experience shaped how I think as a data engineer. I have worked on the reliability side of a production data platform — tracing where data broke and why. Now I aim at building data systems end to end.

As an alternate interest area, I have done substantial research on why LLMs quietly fold when you push back on them. Now, aiming ACL 2027 submission.

view work → / query portfolio github ↗ resume ↓
impact at HPE · production
−40%
mean time to resolve incidents
−55%
validation cycle time
+15%
ML triage accuracy
15+
microservices debugged
stream://utkarsh.events
consuming
0 events
topic: portfolio.v3
lag: 0ms
offset 0
01

skills.

toolkit, grouped by area
01
Data Engineering
batch, streaming & lakehouse
Apache SparkPySparkSpark Structured StreamingKafkaAirflowdbtDatabricksLakeflowAuto LoaderDelta LakeUnity CatalogDuckDBParquetPostgreSQLMySQL
02
ML / AI
modelling & deep learning
PyTorchHugging Face Transformersscikit-learnstatsmodelsNumPySHAPpandasMLflow
03
Cloud & DevOps
cloud platforms, containers & CI
GCPBigQueryGCSAWSS3LambdaDockerDocker ComposeJenkinsCrowdStrike
04
Languages
core languages
PythonSQL
02

projects.

deployable, instrumented, in production
one fact, two truths AT&T · FY2021 revenue · as the market knew it restated 2023-02-13 FY2022 10-K · WarnerMedia spin-off $168.9B $134.0B as_of('2022-06-01') as_of(today) 2022 2024 2026 21.8M knowledge intervals · 14,885 companies · 6 invariants asserted
Data Engineering shipped

Hindsight — a warehouse that remembers what people knew, and when

Companies quietly correct their past financial results, and every database overwrites the original. Backtest on that and you're trading on numbers nobody had at the time. Hindsight ingests 69 quarters of SEC XBRL filings (181M facts) through a Lakeflow medallion pipeline, then resolves per-fact filing precedence into 21.8M knowledge intervals — so any historical date returns only what was publicly knowable then. Measured the resulting look-ahead bias at 3.3% of top-decile stock selections across 49 quarters.

181Mfacts
21.8Mintervals
0.001%broken rows
databrickslakeflowdelta lake auto loaderunity catalogpysparkpytest
→ source code
KAFKA trade.events ticker-keyed SPARK structured streaming VWAP 1min · 30s wm 3 detection signals bronze raw trades silver vwap windows gold anomalies BQ dbt p99 ≈ 58ms · 5 instruments · sub-60s end-to-end 3 detection signals · 8 dbt tests · fault-tolerant checkpointing
Data Engineering live

MarketPulse — real-time market anomaly pipeline

Equity trade events stream through Aiven Kafka (SSL/TLS, ticker-keyed) into PySpark Structured Streaming with 1-min tumbling VWAP windows and 30s watermarking. Medallion lakehouse on GCS with 3 detection signals — Z-score volume spike, intra-window price deviation, wash trading — each with per-signal confidence. Gold lands in BigQuery via 3 dbt models with 8 passing data quality tests.

<60slatency
5instruments
8/8dbt tests
kafkaspark structured streamingdelta lake gcsbigquerydbtdocker
→ source code
NLP · Research ACL ARR · ACL 2027

Sycophancy under pressure — predicting LLM capitulation

First-authored paper investigating hidden-state representation shifts in LLMs before sycophantic flips. Novel monotonically escalating pressure schedule across 5 architectures and 150+ probes. Cosine similarity disruption at the first pressure turn predicts behavioural flip 3–4 turns ahead — without any probe training.

L28dominant layer
75.5%probe acc.
+11.7over chance
pytorchqwen2.5-7b hidden state probingrbf svm
↓ research deep-dive → source code
Data Engineering live demo

SoundStream Analytics — 46M record music ELT

Batch ELT pipeline processing 46M+ records from Spotify Charts, Spotify Songs and Last.fm. Medallion architecture orchestrated as an Airflow DAG; 60% storage compression via partitioned parquet; Silver-layer quality checks dropped 5,043 duplicates across a 36.7% cross-source match rate.

46M+records
60%compressed
70+countries
pysparkdbtairflow duckdbstar schemastreamlit
→ source code
Data Science

Credit Risk Strategy Engine

Hypothesis-driven EDA on 113K+ loans. Kaplan-Meier survival revealed 70% of defaults show distress within 12 months. HistGradientBoosting on 14 bureau features + counterfactual A/B framework recovered $7.8M in loan volume with 20% default reduction. FCRA-compliant SHAP adverse-action codes.

113Kloans
$7.8Mrecovered
-20%defaults
histgradboostshap counterfactual a/bkaplan-meier
→ source code
Data Engineering

Stock Portfolio Manager

End-to-end pipeline pulling real-time market data from Finnhub API → transformed via SQL stored procedures → normalised MySQL → served as portfolio analytics through a Flask REST API with a React frontend.

RESTapi
MySQLstore
Reactui
pythonmysql flaskreactfinnhub
→ source code
Build you're here

this site — a queryable portfolio

The site you're reading is itself a small experiment: a portfolio that behaves like one of my pipelines. Stream console replaying real visitor events, live interpretability widget, and a SQL-ish command palette that actually queries the page. Press / to try.

htmlcssvanilla jsno framework
→ source code → open console
03

research.

when the model caves — and how to see it coming
ACL ARR · May '26 Northeastern

"Before the Model Caves —
Detecting Pre-Capitulation States in Multi-Turn Sycophancy"

Sycophancy in LLMs is usually studied after the model flips. We asked the opposite question: can you tell, from the hidden states alone, that a flip is about to happen — before any visible change in the output?

We built a monotonically escalating pressure schedule across five turns and traced hidden-state activations through every transformer layer. The signal was there, and it was loud. In Qwen2.5-7B, Layer 28 dominates; across all five models, layers 17–19 are globally predictive — a dissociation unreported in prior work.

key finding cosine similarity disruption at the first pressure turn predicts behavioural flip 3–4 turns in advance, with no probe training required. RBF SVM + KNN classifiers reach 75.5% accuracy — +11.7 over chance.

First author with Soham Padia (equal contribution); with Tomas D'Avola, Vedant Shah; advised by Prof. Malihe Alikhani. Targeting ACL 2027.

qwen2.5-7b · layer activations L2 norm, normalised
pressure schedule ← drag through turns to see hidden state →
activation pattern at turn 0
stable · model holding original position
04

experience.

log // tail -f career.events
Sep 2026 — present
Boston, MA
Graduate Teaching Assistant
Natural Language Processing, Khoury College. Office hours, homework support and concept review for a graduate cohort working through tokenization, embeddings and attention.
  • Run weekly office hours and concept reviews on NLP fundamentals: tokenization, embeddings, attention, and why the loss curve flatlined
  • Walk students through homework problems and debug their code with them, without handing over the solution
  • Help write homework assignments on NLP foundations: feedforward neural networks, SVD, word embeddings and transformers
  • Grade assignments and share common mistakes with the instructor
nlpteaching pytorchtransformers
Jan 2022 — Aug 2025
Bangalore, IN
Cloud Developer - Hewlett Packard Enterprise
Switch Data Monitoring — the telemetry platform ingesting hardware health and network metrics from HPE's enterprise switch fleet across 10+ models, through an enricher → predictor → sink connector chain. I worked the reliability side: where data broke, why, and keeping validation honest as the platform moved underneath it.
15+microservices
−40%mttr
−55%cycle time
4K+failure labels
Cloud Developer Aug 2022 — Aug 2025 · 3 yr 1 mo
  • Traced data loss across 15+ microservices ingesting VLAN/VXLAN switch telemetry, following records through enricher → predictor → sink connectors to pinpoint the failing service and root cause → −40% MTTR
  • Built training dataset from 4,000+ failure logs, designed annotation schema for an ML triage assistant → +15% classification accuracy, removed manual escalations
  • Designed a parallel execution framework distributing validation scripts across heterogeneous switch fleets → −55% end-to-end cycle time
  • Owned Jenkins CI for the platform's test suite and lab environments; kept validation coverage current as GraphQL APIs and deployed services drifted from test expectations
  • Mentored 3 interns on automation workflows; documentation reduced onboarding by 1–2 months
Software Engineer Intern Jan 2022 — Jul 2022 · 7 mo
  • Built automated feature-validation scripts integrated into the CI pipeline across 10+ switch models; eliminated recurring production rejections from malformed telemetry payloads
  • Cross-referenced 500+ historical debugging logs to verify log-extraction accuracy; authored the Confluence reference adopted for stack onboarding
pythonjenkins ci sqlgraphqlcrowdstrikedockerconfluence
05

education & off-screen.

how I got here and what I do when the laptop is closed
Northeastern University
MS · Computer Science · Boston, MA
Sep 2025 — May 2027 (expected)
coursework MLOps · NLP · Data Mining · Database Management Systems · Algorithms for Data Science · Deep Learning
Manipal Institute of Technology
BTech · Electronics & Communication · India
May 2022 minor — data science & modelling
coursework Data Structures · Data Science · Python · Cloud Computing · Data Modelling
[01]

football — vice-captain, weekend referee

Vice-captain of MIT Manipal's inter-college team (20+ players, regional tournaments). 10+ years of playing.

[02]

HPE promotion track

Approved for promotion based on contributions to the automation framework and the ML-powered triage initiative. Multiple team recognition badges.

[03]

student governance

Member of the Official Student Committee at MIT Manipal — campus initiatives, event ops, liaison between students and administration.

[04]

off-keyboard

Football. Movies and shows. Tech blogs. Pattern-matching across domains is the actual job.

let's build something.

Open to May 2027 full-time roles
in Data Engineering, Data Science, and ML Engineering.

→ email me ↓ download resume / open query console
email saraogi.u@northeastern.edu linkedin /in/us1610 ↗ github /utkarsh1610-s ↗