Hi

I'm

Siddhant Rajhans.

I'm a Machine Learning Engineer specializing in LLM evaluation and AI security. I'm a contributor to EleutherAI's lm-evaluation-harness, a published researcher (IEEE, Springer), and I've built production AI at scale (1M+ records/month) with monitoring, guardrails, and responsible-AI practice.

→ Say Hi See my open source
Siddhant Rajhans
Merged PR to EleutherAI's
lm-evaluation-harness 3 peer-reviewed papers
IEEE · Springer 1M+ records / month
in production PyPI · HF published
open-source toolkit

01 / Selected Work

Explore My Latest Projects

CortexLab Architecture

CortexLab: Brain Encoding Toolkit

Multimodal fMRI brain encoding toolkit built on Meta's TRIBE v2. GPU voxelwise ridge (Triton), causal modality lesion analysis, brain-alignment benchmarking, 3D brain viewer, live inference from webcam/screen/video. 143 tests, 10 contributors, published on PyPI and HuggingFace.

PyTorchTritonfMRI3D VizLive Inference Code
Bloomberg Sentiment x FinBERT Architecture

Bloomberg Sentiment × FinBERT

Empirical test of whether Bloomberg's NEWS_SENTIMENT_DAILY_AVG can be replicated with open-source FinBERT on a 30-stock S&P 100 universe (2018-2026, 62.8K stock-day obs). Multi-horizon IC, long-short quintile backtest, Fama-French 3 with Newey-West HAC. Replication fails (ρ = −0.26) — and that's the point.

Bloomberg APIFinBERTstatsmodelsFama-FrenchNewey-West Code
DreamStudio Architecture

DreamStudio: AI Cinematic Story Director

AI-powered cinematic story director. Speak naturally, point your camera, and watch scenes materialize as images, video, and music in real-time. Full-stack app with web, mobile, and Python backend.

Gemini LiveImagen 4Veo 3.1Lyria 2FlutterPython Code
Data Pipeline Architecture

Messaging-Based Data Pipeline

End-to-end streaming pipeline processing 1M+ records/month with 65s latency (p95). Kappa architecture with event-time processing, watermarking, and fault tolerance built for bursty event ingestion.

KafkaPySparkDockerAirflowHiveNiFi Code
Multimodal RAG Architecture

Multimodal RAG for Scientific Literature

Textual + multimodal RAG over 500K+ papers with a LangGraph agent that runs a grounding-validation step, flagging weakly-supported answers instead of returning them (a hallucination guardrail). FAISS retrieval with cross-encoder reranking; 94% recall on an internal evaluation set.

LangGraphSciBERTCLIPTAPASFAISSGrounding Code
Bike Lane Sentinel Architecture

Bike Lane Sentinel

Computer vision system that monitors illegal vehicle encroachment into NYC bike lanes and automatically alerts NYC DOT. Real-time detection with interactive dashboard and evidence capture.

Computer VisionTypeScriptReactNode.jsReal-time Code

02 / Open Source

Open Source & Contributions

PR #3662 · Merged

EleutherAI lm-evaluation-harness

Contributed InfiniteBench — 11 long-context evaluation tasks (retrieval, code, math, novel QA, dialogue, EN/ZH) — to the field-standard open-source LLM evaluation framework used for benchmarking, red-teaming, and safety evaluation. 799 lines across 15 files, with scoring matched to the official implementation.

LLM EvaluationPythonLong-ContextBenchmarks
PyPI · HuggingFace · Live Demo

CortexLab

Open-source fMRI brain-encoding toolkit extending Meta's TRIBE v2. Published on PyPI (cortexlab-toolkit) and HuggingFace, with a live demo, 143 tests, and 9 community contributors.

GitHub PyPI Live Demo

03 / Experience

Built Production Systems & Shipped Real Products.

Oct 2023 – Dec 2024

Junior Machine Learning Engineer

Seed-Stage Health-Tech Startup (NDA)

  • Led the retrieval and prompt-orchestration workstream of an agentic AI system powering personalized clinical-facing interactions, raising user engagement by about 25%.
  • Built transformer-based NLP and multimodal retrieval for clinical notes, lab reports, and diagnostic documents with clinical and product teams, improving retrieval accuracy by 30%.
  • Lowered the agent's serving cost by routing simple requests to a small fine-tuned model and caching retrieval, keeping the large model for the hardest 25% at under 5 s p95.
  • Designed and shipped streaming ML pipelines on AWS (Kafka, Airflow, Docker) with the data engineering team, processing 1M+ healthcare records/month at under 65 s p95 latency.
  • Built monitoring and validation checks for data drift, prediction quality, and data integrity across clinical ML workflows.
AWSKafkaAirflowDockerNLPAgentic AI
Apr – Sep 2023

Software Development Engineer Intern

Seed-Stage Health-Tech Startup (NDA)

  • Reduced average API request latency by 40% by moving synchronous flows to async processing, and added caching and request batching to ML model serving.
  • Strengthened API security for sensitive healthcare data with senior engineers: input validation, authentication middleware, and audit logging.
ML ServingAPIsBackend OptimizationSecurity

04 / Toolkit

Technologies and Tools I Work With

LLM Evaluation & AI Security

LLM Evaluationlm-evaluation-harnessRed-teamingGuardrailsGrounding / FaithfulnessModel Monitoring & DriftResponsible AI (NIST AI RMF)

LLM, Agents & RAG

LangGraphRAGAgentic OrchestrationTool CallingPrompt EngineeringBenchmark Design

Core ML & Deep Learning

PyTorchTensorFlowScikit-learnTransformersHugging FaceCNNs

Data, Infra & MLOps

PythonSQLApache SparkKafkaFAISSPostgres/PgvectorAWS (SageMaker, S3)DockerAirflowMLflowW&B

05 / Research

Research Publications

Peer-reviewed work in AI security and trust — deepfake detection, ML for cybersecurity, and threats in AI-integrated cloud systems.

IEEE ICCE 2025

CNN-Based Detection Mechanism for Deepfake Image

A Mishra, S Rajhans, BB Gupta, KT Chui

View on Google Scholar
Springer, ICRTC 2025

The Evolving Landscape of Cloud Computing: AI Integration, Threats, Challenges and Security Concerns

P Singh, S Rajhans

View on Google Scholar
Springer, ICSPN 2023

Machine Learning and AI in Cybersecurity: Insights and Solutions

S Rajhans, A Mishra

View on Google Scholar

06 / Writing

From the Blog

Notes on building ML systems, evaluating frontier models, and lessons from production.

evaluation

Building an LLM Evaluation Framework from Scratch

Why off-the-shelf benchmarks aren't enough, and how I built a custom harness with consistency scoring, calibration, and chain-of-thought quality analysis.

Read rag & agents

Lessons from a Multimodal RAG System over 500K Papers

Architecture decisions, FAISS optimization, and why agent evaluation is harder than agent building. From processing 2.3M figures, 890K tables, and 410K equations.

Read research tooling

Building CortexLab on Meta's Brain-Encoding Model

Extending TRIBE v2 with streaming inference, modality attribution, brain-alignment benchmarking, and cognitive-load scoring, built into a released toolkit.

Read
Read all posts

07 / Education

Education & Credentials

2025–2026

MS in Machine Learning

Stevens Institute of Technology

Hoboken, NJ
2019–2023

B.Tech in Computer Science & Engineering

Swami Rama Himalayan University

Dehradun, India

Certifications

Weights & Biases Training & Fine-tuning LLMs Verify credential
Stanford / Coursera Machine Learning Verify credential
NVIDIA Generative AI with Diffusion Models Verify credential
IBM Cloud Computing Diploma Verify credential

08 / Contact

Let's build something.

Graduating December 2026. Open to Applied AI, ML, and research-engineering roles, especially in LLM evaluation and AI security. Based in Hoboken, NJ; open to New York and remote.

→ Get in touch Download resume