// hire_me()
OPEN TO WORK · AI Engineer · ML Engineer · Applied Scientist
// jersey_city:NJ · ms_ai@yeshiva · graduating Dec 2026

TIRTH
JOSHI.

// researcher
5 papers · 4 advisors · IEEE ICNC · ACM · NeurIPS · ECCV
+
// engineer
LLM · RL · Graph ML · Blockchain · Production systems
role ::=AI_Engineer && Researcher
edu ::=MS_AI @ Yeshiva · GPA 4.0/4.0
papers::=5 papers + 1 abstract accepted [IEEE·ACM·NeurIPS·ECCV]
stack::=Python · PyTorch · LangChain · Docker · gRPC · Neo4j
avail::=immediately · full-time · US authorized
// knowledge_graph.animate()
scroll
01//about.md
tirth@yu:~$ cat bio.txt

/* the core question */

"How do we build AI systems that reason, adapt,

and stay reliable in complex real-world settings?"


depth > breadth

systems > demos

clarity > hype


// research streams [active]

├─ LLM security · smart contract vuln detection

├─ Multi-agent RL · heterogeneous IoT/robotics

├─ Compositional privacy risk · re-identification

└─ Topology-based gradient descent optimization


// also selected for RLSS 2025

$ rl_summer_school = "accepted · rlsummerschool.com"

# (couldn't attend · financial/personal reasons)


// fun_facts.sh

$ eq_of_life = "riemann_hypothesis"

$ hobbies = [math, poetry, food, finding_good_restaurants]

$ languages = [English, Gujarati, Hindi]

$ // 🔍 secrets hidden on this page...

0
papers & abstracts
0
research advisors
0
github repos
0.0
GPA / 4.0
// currently_seeking[]
AI Engineer ML Engineer Applied Scientist Research Engineer LLM Engineer
// research_interests[]
LLM_SecurityMARLPrivacy_Theory Graph_MLTopology_AIDeFi_Mechanisms Blockchain_SecIoT_RoboticsQuantum_ML
// recognition[]
★ Best Research Award — YU CSE Day 2025 ◈ IEEE ICNC 2026 — Invited Paper (Main Program) ▲ Top 0.80% AWS DeepRacer (Rank 19/2,362) ✓ Selected — RL Summer School 2025 ◉ YU Symposium 2025 — Upcoming Speaker
02//what_i_build.sh

/* pragmatic AI engineering */

I ship production systems. Research depth + engineering pragmatism — not demos, real deployed systems.

LLM Systems & Agents

End-to-end LLM application development — RAG pipelines, tool-using agents, multi-step planners, structured output, evaluation frameworks. LangChain / LangGraph / custom orchestration.

LangChainLangGraphRAGHuggingFaceOpenAI
// shipped:
Cross-chain DeFi agent · NL interface cutting manual input 40%
🧠

Reinforcement Learning

Policy training (PPO/DQN/SAC), reward engineering, multi-agent systems, online adaptation. From simulation to hardware — OpenAI Gym, Stable-Baselines3, custom environments.

PyTorchPPODQNSACOpenAI_Gym
// shipped:
DeepRacer PPO agent · Top 0.80% global · Multi-agent IoT coordination
🕸

Graph ML & Reasoning

Graph Neural Networks, knowledge graphs, Neo4j, hierarchical graph representations, pathfinding over complex networked systems. Graph-as-reasoning-substrate.

Neo4jGNNThe_GraphNetworkXPyG
// shipped:
IEEE ICNC 2026 — GHP algorithm · 8× faster cross-chain routing
🔐

ML Security & Privacy

Adversarial ML, smart contract vulnerability detection, re-identification risk quantification, privacy-preserving systems. Building AI that stays safe when attacked.

SolidityPrivacy_MetricsRed_TeamingGDPR
// research:
RPI metric · ECCV · APF · ACM FAccT submissions

Production ML Infrastructure

Microservices, gRPC/REST APIs, Docker, vector databases, CI/CD, load balancing. Taking ML models from notebook to production at scale.

FastAPIDockergRPCFAISSPinecone
// shipped:
25k req/day LLM backend · API latency 2.1s → 0.6s · 43% uptime ↑

Blockchain & DeFi AI

Cross-chain intelligence, LLM-integrated DeFi automation, smart contract security tooling, on-chain AI agents. Intent-based interfaces for complex decentralized systems.

LI.FICircleLayerZeroOceanThe_Graph
// shipped:
Synapse @ ETHGlobal NYC · 27% gas savings · NL DeFi commands
27%
gas cost reduction · DZap
3.5×
API speed · ComputeLib
routing speed · IEEE paper
43%
uptime improvement
~40%
manual input reduction
03//research.active

/* four concurrent research directions */

📢 UPCOMING TALK
"When 'Anonymous' Data Stops Being Anonymous: Measuring How Public Data Accumulates into Re-Identification Risk"
YU Symposium 2025 · Yeshiva University
📢 UPCOMING TALK
"Morse-Seeded Coresets for Structure-Preserving Landmarking on kNN Graphs"
Network Science Informs AI (NSIA) · NetSci 2026
[ 01 ]
Prof. Shucheng Yu · Yeshiva University

LLM Security & Smart Contract Vulnerability Detection

RL-based synthetic dataset generator for adversarial Solidity contracts targeting underrepresented vulnerability classes — including zero-day patterns. LLM detection framework with RL-style feedback loops iteratively refining policies from sparse execution signals.

LLMsRLSolidityAdversarial_MLZero-Day
[ 02 ]
Prof. Honggang Wang · AIM Lab · IEEE Fellow

Multi-Agent RL for Heterogeneous IoT & Robotics

RL-based coordination for heterogeneous IoT — jointly training a humanoid robot and RC vehicle across vision, audio, and motion modalities. Partial observability, inter-agent communication, real-time sensor fusion constraints.

MARLPPOSensor_FusionRoboticsIoT
[ 03 ]
Prof. Aaron Ross · Yeshiva University

Compositional Privacy Risk & Re-Identification Theory

Re-Identification Pressure Index (RPI) — quantifying anonymity erosion through cumulative data releases and cross-linkages using entropy and collision probability. Multiple submissions to ACM FAccT, ECCV, APF, NeurIPS.

PrivacyInfo_TheoryRPIGDPRFAccT
[ 04 ]
Prof. Marian Gidea · Yeshiva University

Topology-Based Optimization of Gradient Descent Initialization

Applying topological data analysis (TDA) and Morse theory to improve gradient descent initialization strategies. Using structural properties of loss landscapes — coresets, persistent homology — to inform smarter, structure-preserving starting points for optimization.

TDAMorse_TheoryOptimizationTopologyGD
04//git log --experience

Work history_

Jan 2026 present ● active
Yeshiva University — Katz School of Science & Health · New York
// Research Assistant (×4 concurrent advisors)

Four parallel research streams under Profs. Shucheng Yu, Honggang Wang, Aaron Ross, and Marian Gidea spanning LLM security, IoT multi-agent RL, compositional privacy theory, and topology-based optimization.

Sep 2024 Dec 2024
DZap · Bangalore
// AI Engineer

Designed inter-chain path-finding framework — cross-chain routing as sequential decision-making over dynamic gas costs and liquidity constraints. Built LLM-integrated blockchain agents for natural-language DeFi commands via multi-agent planning.

27% gas cost ↓ ~40% manual input ↓
Graph_MLLLM_AgentsDeFiMulti-AgentBlockchain
Jun 2023 May 2024
ComputeLib · Delhi
// Machine Learning Intern

gRPC/REST microservices, Hugging Face + LangChain LLM backend (~25k req/day), Docker containerization and load-balancing. Brought API latency from 2.1s to 0.6s.

3.5× API speedup 43% uptime ↑ 25k req/day LLM
LangChainDockergRPCVector_DBsMicroservices
Apr 2023 Dec 2023
Skiome · Gandhinagar
// Co-Founder & CTO

Co-founded a Startup India-recognized venture; led product architecture, web development, and technical execution across a small founding team.

37% time-to-action ↓
LangChainDockergRPCBusinessStartup
Jul 2022 May 2024
IIIT Vadodara
// Research & Teaching Assistant

Research under Dr. Jignesh S. Bhatt on cognitive systems with generative networks and stochastic modeling. TA for ML, Probability & Statistics, and Introduction to Programming.

Feb 2023 Mar 2023
Ministry of Education, Government of India
// Technical Intern (Android)

Cultural preservation — archiving oral Gujarati lullabies. Firebase: −23% data exchange, −12% per-session download.

05//publications.bib

Research output_

🎤
Upcoming Presentation · YU Symposium 2025 — "When 'Anonymous' Data Stops Being Anonymous: Measuring How Public Data Accumulates into Re-Identification Risk"
🎤
Upcoming Poster · Network Science Informs AI (NSIA) 2026 — "Morse-Seeded Coresets for Structure-Preserving Landmarking on kNN Graphs"
✓ ACCEPTED IEEE ICNC 2026

Hierarchical Graph Representation for Multi-Chain Blockchain Routing

Tirth Joshi, Honggang Wang

Proposes hierarchical AND/OR graph for multi-chain ecosystems. GHP algorithm: 8× faster than traditional approaches within ~5% of optimal across tens of thousands of tokens and dozens of chains. Featured in YU official news.

IEEE ICNC 2026 · Maui, HI · Feb 2026 · ISBN 979-8-3315-7111-5 dblp ↗
◆ ABSTRACT ACCEPTED NetSci 2025 · NSIA Satellite

Morse-Seeded Coresets for Structure-Preserving Landmarking on kNN Graphs

Tirth Joshi

Abstract accepted at NSIA — a satellite event of NetSci 2025 (Network Science). Introduces Morse-theory-seeded coreset construction for structure-preserving landmark selection on k-nearest-neighbor graphs, preserving topological features under dimensionality reduction.

NSIA Satellite @ NetSci 2025 · Network Science
◎ UNDER REVIEW ECCV

Compositional Non-Face Re-Identification Pressure under Cumulative Vision Releases

Tirth Joshi et al.

Measures cumulative re-identification risk as vision datasets and models accumulate combined signals over time — even without explicit face identifiers. Formalizes how non-face visual cues compose into re-id pressure.

European Conference on Computer Vision (ECCV)
◎ UNDER REVIEW NeurIPS

On the Limits of Semantic Reconstruction Through Text: A Bottleneck Theory with Structured Scene-Level Distortion

Tirth Joshi et al.

Formalizes fundamental limits of semantic reconstruction from text using information-bottleneck theory, introducing structured scene-level distortion measures that bound what can be recovered from natural language descriptions alone.

Neural Information Processing Systems (NeurIPS)
◎ UNDER REVIEW ACM FAccT

Measuring the Statistical Erosion of Anonymity: A Historical Analysis of Re-Identification Potential

Tirth Joshi, Aaron Ross

Introduces the Re-Identification Pressure Index (RPI) — quantifying how cumulative data releases and cross-linkages erode anonymity over time using entropy and collision probability.

ACM Conference on Fairness, Accountability, and Transparency
◎ UNDER REVIEW APF

Re-Identification Pressure under GDPR: Measuring Cumulative Identifiability in Data Ecosystems

Tirth Joshi et al.

Applies re-identification pressure framework to GDPR-governed data ecosystems, measuring how compliant releases can cumulatively erode privacy guarantees across data subjects and time horizons.

Annual Privacy Forum (APF)
⟳ TO BE SUBMITTED AFT

Soft-Landing Liquidations for Overcollateralized Lending

Tirth Joshi et al.

SLLA replaces hard liquidations with smooth tranche-based auctions modeled as constrained sequential control — cutting bad debt by ~45%. Targeting ACM Advances in Financial Technologies (AFT).

ACM Advances in Financial Technologies (AFT) — submission in preparation
★ BEST RESEARCH AWARD YU CSE Day + DuckAI 2025

Do Phonetic Patterns Predict Grammatical Structure?

Tirth Joshi

Cross-linguistic ML study using IPA-converted Bible corpora. Pipeline: IPA conversion → typological labeling → leave-one-language-out (LOLO) evaluation. Best Research Award at YU CSE Research Day Fall 2025. Poster at DuckAI 2025 @ Stevens Institute of Technology.

YU CSE Day 2025 · DuckAI 2025 @ Stevens Institute of Technology
06//ls -la ./projects/

Things I've built_

⛓ hackathon

Synapse

ETHGlobal NYC 2025

"Google Maps for token flows." Cross-chain investment co-pilot: Ocean Protocol + Neo4j + The Graph + ASI-1 Mini LLM + MeTTa logic. Risk guardrails: slippage caps, protocol allowlists, position limits.

LangGraphNeo4jThe_GraphOceanLI.FI
🏎 competition

Autonomous Racing Agent

AWS DeepRacer — Rank 19/2,362 · Top 0.80% Globally · Semi-Finalist

Continuous-control PPO agent with engineered reward functions combining speed, steering smoothness, and track-center deviation. AWS AI & ML Scholarship awarded.

PPOReward_EngineeringAWSRL
🎮 rl-research

Adaptive Game Agent

Real-Time Opponent Modelling

Game agent learning opponent behaviour via online RL, adapting policy dynamically without resets — demonstrating non-stationary policy adaptation under distribution shift.

Online_RLNon-StationaryPolicy_Adapt
🏛 open-source

Political Bonds RAG

Indian Electoral Bonds Transparency Tool

RAG-based NL query interface over India's Electoral Bonds disclosure data (released post-SC ruling 2024). Making opaque public data actually queryable.

RAGLLMVector_DBPython
📖 llm-app

Build Your Own Story

Interactive Branching LLM Narrative

Branching storytelling with LLM-generated prompts and AI-generated images. Each choice forks the narrative — no pre-written paths. Fully dynamic generation.

LLMGenAIInteractive
🎵 civic-tech

Gujarati Lullaby Archive

Ministry of Education, Govt. of India · 2023

Android app for cultural preservation of oral Gujarati lullabies. Firebase: −23% data exchange, −12% per-session download. Code as cultural preservation.

AndroidFirebaseJava
07//package.json

Technical stack_

// rl_ml_frameworks
PyTorchTensorFlowscikit-learnOpenAI_GymStable-Baselines3PPODQNSACKerasMLflow
// llms_retrieval
LangChainLangGraphHuggingFaceFAISSChromaDBPineconeQdrantOpenAI_API
// backend_infra
FastAPIFlaskDjangoDockergRPCRESTNginxJWTMicroservices
// databases_graphs
Neo4jThe_GraphMySQLMongoDBFirebaseCockroachDBFAISS
// web3_defi
SolidityLI.FILayerZeroCircle_WalletsOcean_ProtocolASI-1_MiniMeTTa
// languages
PythonC/C++TypeScriptJavaKotlinSQLRC#
09//contact.init()
// open_to_work = true
AI Engineer · ML Engineer · Applied Scientist · Research Engineer · LLM Engineer
US authorized · Available immediately · Open to remote, hybrid, on-site
⚡ Let's talk

Get in touch_

Open to research collaborations, full-time roles, and good food recommendations.