$ init utkarsh.saraogi --target=portfolio
[ ok ] mounting /skills 82 chips loaded
[ ok ] connecting github://utkarsh1610-s 5 repos
[ ok ] bootstrapping lineage.dag 4 layers, 28 nodes
[ ok ] warming stream.console subscribed → 6 topics
[ ok ] ready. press / to query.
LIVE
/
utkarsh.saraogi
/
Boston, MA
/
—
open to co-op · Fall '26
query /
open to Fall '26 · Spring/Summer '27 co-op
Utkarsh Saraogi

Utkarsh
Saraogi.

$ role =

Three years at HPE taught me what actually breaks data systems at scale — not the theory, but upstream payload drift at 2am, silent fan-out failures across 15 services, and the gap between what a model claims to do and what it does under load.

Now at Northeastern's MSCS program I build real-time lakehouses with Kafka and Spark, run counterfactual A/B on credit risk, and research why LLMs quietly fold when you push back on them.

view work → / query portfolio github ↗
stream://utkarsh.events
consuming
0 events
topic: portfolio.v3
lag: 0ms
offset 0
01

snapshot.

what the numbers say
recovered $7.8M counterfactual A/B · credit risk · 113K loans
records processed 46M+ ELT · 3 raw sources · 70+ countries
MTTR reduction −40% 15+ microservices · telemetry triage
flip prediction 3-4turns sycophancy paper · hidden state probing
storage compression 60% partitioned parquet · medallion
streaming latency <60s MarketPulse · Kafka → Spark → BigQuery
02

lineage.

how raw experience flows to gold
raw BRONZE
▢ HPE · 3 yr cloud dev 2022–25
▢ Northeastern MSCS 2025–27
▢ Alikhani Lab · NLP 2026
skills SILVER
⊡ Jenkins CI/CD
⊡ Docker · containers
⊡ CrowdStrike telemetry
⊡ DevOps · GCP · AWS
⊡ Kafka · Spark Streaming
⊡ PySpark · dbt · Airflow
⊡ Hidden-state probing
⊡ Causal · A/B · SHAP
projects SILVER
▣ MarketPulse
▣ SoundStream Analytics
▣ Credit Risk Engine
▣ Sycophancy Detection
▣ Stock Portfolio Mgr
outcomes GOLD
★ −40% MTTR
★ shipped to prod
★ 4K+ failure labels
★ ACL ARR submission
★ $7.8M recovered
★ sub-60s latency
tip hover any node to trace its upstream + downstream dependencies →
03

projects.

deployable, instrumented, in production
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 → read more
NLP · Research ACL ARR May'26

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 → github
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 → live demo ↗
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
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
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, interactive lineage DAG, live interpretability widget, and a SQL-ish command palette that actually queries the page. Press / to try.

htmlcssvanilla jsno framework
→ open console
04

research.

when the model caves — and how to see it coming
ACL ARR · May '26 Alikhani Lab · 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 EMNLP main · BlackboxNLP backup.

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
05

experience.

log // tail -f career.events
Sep 2025 — present
in progress
Graduate Researcher @ Alikhani Labs · Northeastern Boston, MA
  • First-authored ACL ARR submission on detecting pre-capitulation states in multi-turn LLM sycophancy — targeting EMNLP main, BlackboxNLP backup
  • Engineered the monotonically escalating pressure schedule that became the paper's central novelty; ran the experiment matrix across 5 architectures × 150+ probes
  • Localised the predictive signal: Layer 28 dominant in Qwen2.5-7B, layers 17–19 globally predictive — a dissociation unreported in prior sycophancy literature
Aug 2022 — Aug 2025
Cloud Developer @ Hewlett Packard Enterprise Bangalore, IN
  • Monitored distributed telemetry flows across 15+ microservices ingesting VLAN/VXLAN switch metrics; root-caused upstream payload drift across enricher → predictor → sink connectors → −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/CD lifecycle; implemented data-contract validation gates before production promotion
  • Mentored 3 interns on automation workflows; documentation reduced onboarding by 1–2 months
Jan 2022 — Jul 2022
Software Engineer Intern @ Hewlett Packard Enterprise Bangalore, IN
  • Built automated feature-validation scripts integrated into the CI pipeline; eliminated lint-related production rejections
  • Authored Confluence reference used across the team for switch monitoring stack onboarding
06

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). Currently refereeing competitive matches on weekends — 10+ years of playing. The pattern-recognition transfers cleanly to production triage.

[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 Fall '26 and Spring/Summer '27 co-op + internship roles
in Data Engineering, Data Science, and ML Engineering.

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