Bhanu Prakash Vangala

Columbia, MO · GPA 3.9 / 4.0

• Thesis area: trustworthy and reproducible LLM-based agentic systems; multi-model orchestration; provenance tracing.
• Advised by Dr. Tanu Malik (Radiant Lab).
• Google Ph.D. Fellowship Nominee (NLP track, 2025); EECS Travel Fellowship ‘26; Chameleon top-10 presentation ‘26.

Columbia, MO · GPA 4.0 / 4.0

• Thesis: Deploying LLMs as a Service in a Kubernetes HPC Cluster.
• Advised by Dr. Grant J. Scott and Dr. Jianlin Cheng.
• Outstanding Master’s Student Award (2025); Runner-up, MUIDSI Hackathon (2025).

Vellore, India · GPA 8.8 / 10

• Thesis: Multilingual Sentiment Analysis on KOO User Posts.
• Advisors: Dr. P. Kumaraguru (IIIT Hyderabad) and Dr. Soughbhagya.
• Dean’s Research Excellence Award (2023); Top-2 Academic Performer (2022); Merit Scholarship.

Bhanu Prakash Vangala, Tanu Malik

Three agents, four languages, fifty tasks. Dependency-set agreement falls as low as 7% on identical tasks, and newer agents show no improvement.

Under review · AI Magazine

Bhanu Prakash Vangala, Nagarjuna K., Tanu Malik

CAMP: selective eBPF / strace auditing with NGBoost LogNormal predictors; median APE reduction across 35K+ Slurm tasks on AWS ParallelCluster.

Under review · IEEE Cluster 2026

Bhanu Prakash Vangala, Ashish Gehani, Tanu Malik

A reproducibility-aware evaluation that scores environment specification, build reliability and runtime behaviour, not just whether the tests pass.

ACM REP 2026 · Oral

Bhanu Prakash Vangala, Tanu Malik

Nine models from 1B to 27B routed by Thompson Sampling with a cold-start state machine. 310,190 requests on NRP Nautilus: 61% GPU utilization against 31% for static deployment, cutting GPU-hours by 46%.

IEEE CLOUD 2026 · Oral

Bhanu Prakash Vangala, Ali Adibifar, Tanu Malik, Ashish Gehani

100 prompts given to Claude, Codex and Gemini. Of the 300 resulting projects only 68.3% ran in a clean container: Python 89%, Java 44%. Agents declared about 3 dependencies per project; the projects pulled in around 49 at runtime, a 13.5x gap.

AAAI 2026 RAI Workshop · Oral Paper

Bhanu Prakash Vangala, Tanu Malik, Ashish Gehani

Multi-agent routing plus GPU orchestration for cost-efficient self-hosted LLM pipelines.

AAAI 2026 DAI Workshop · Oral Paper

Bhanu Prakash Vangala, Tanu Malik

Pick-and-Spin router with serverless GPUs on Kubernetes; balances latency against cost and scales to zero.

ACM SC 2025 · Poster

Bhanu Prakash Vangala, Syed Mahmud, Prabhat Neupane, Janani Selvaraj, Jianlin Cheng

Self-consistency checking, retrieval against curated sources, and a knowledge graph that flags low-connectivity fact fragments. Cuts hallucination rates by about 30% and reaches F1 0.95 on cross-domain inconsistency detection.

AAAI 2025 Spring Symposium · Oral Paper

Syed Mahmud, Prabhat Neupane, Janani Selvaraj, Bhanu Prakash Vangala, Jianlin Cheng

A BigBird span-level classifier: F1 0.947 on MultiNLI and 0.728 on ANAH.

AAAI 2025 Spring Symposium Paper

Bhanu Prakash Vangala, Sowmya Guda, Latha Peddi, Navya Vangala

28.8% of the dominant corpus's official test split has a near-twin in its own training split; a second corpus leaks 22.3% byte-identically; 95.5% of traceable test images share a patient with training; file headers containing no anatomy separate tumour from no-tumour at 0.959 balanced accuracy.

Under review · IEEE JBHI

Bhanu Prakash Vangala

Eight pretrained backbones differ by only 0.026 AUROC, but freezing versus fine-tuning moves AUROC by 0.044 and changing the decision threshold moves balanced accuracy by 0.090. A file-properties-only classifier with no anatomy reaches 0.992 in the training pool and 0.496 on the official split.

Under review · NeurIPS RMLR

LLMOps · Kubernetes · HPC

With Dr. Tanu Malik (University of Missouri), Dr. Ashish Gehani (SRI International), Dr. Kwo-Sen Kuo (NASA), Dr. Abhilash Jindal (IIT Delhi)

• FlexiFlow: Bandit-based model switching, FastAPI routing with GPU telemetry, Prometheus + Grafana observability. Demonstrated at SIGMOD.
• Pick-and-Spin: Thompson Sampling with a Cold-Start State Machine: 9.2% cold-starts across 310K runs and 61% GPU utilization, against 31% for the static baseline.
• Self-hosting LLMs: Helm + vLLM LLM-as-a-Service on NSF Nautilus with KEDA autoscaling; serverless on AWS SageMaker and Lambda with scale-to-zero.
• Coding-agent reproducibility: 300 repositories generated by Claude, Gemini and Codex, replayed via SLURM; the SciUnit ptrace harness extended to Java and JavaScript.

Agentic AI · MCP · gRPC

With Dr. Tanu Malik (University of Missouri), Dr. Matt Maschmann (University of Missouri), Dr. Derek T. Anderson (University of Missouri)

• MCP & tooling: Authored custom MCP servers and agent skills wrapping Nanoscribe and SEM instrument APIs; ran 50+ automated experiment cycles with per-call provenance.
• Multi-agent orchestration: Coordinated agents with Google ADK and Agent2Agent (A2A) over gRPC and Protocol Buffers, behind a FastAPI control plane with pytest and GitHub Actions CI for reproducible runs.

AI · ML · NLP

With Dr. Jianlin Cheng (University of Missouri), Dr. Grant Scott (University of Missouri), Dr. Prasad Calyam (University of Missouri), Dr. Chitta Baral (Arizona State University), Dr. Lenore Dai (Arizona State University)

• HalluFormer: A BigBird span-level hallucination classifier: F1 0.947 on MultiNLI and 0.728 on ANAH.
• HalluMat: The HalluMatData benchmark with retrieval augmentation over IR, NER and semantic similarity: a 30% hallucination reduction.

Redmond, WA · with Juan-Arturo Herrera, Anqi Cheng, Kyle Hatridge

• Built a reusable temporal featurization framework (TFT / TCN) for predictive Windows retention across 1B+ users, 5,000+ features and 15+ years of Windows and Devices telemetry, a +45% PR-AUC lift over baseline, driven by lag-based trajectory signals with SHAP interpretability.
• Built the Cosmos / SCOPE data layer over Azure streams and data lakes, and automated Copilot Studio feature-analysis workflows.

Columbia, MO

• Radiant Lab (NASA / NSF). Drove NASA-funded research on LLMs, coding-agent reproducibility and dependency resolution; designed the SciUnit ptrace audit harness; first-authored multiple peer-reviewed papers.
• Data Intensive Computing Lab (DoD / NSF). Built hallucination-detection pipelines; delivered a 40% geospatial-accuracy lift on UAV workflows.
• Kubernetes / Helm on NRP Nautilus HPC. GPU quota management and deployment automation for 9 self-hosted LLMs.
• TA, Web Development (MERN). Mentored 115+ students; built CI/CD scaffolding and grading automation on GitLab.

Remote

• Built large-scale web scraping and information-extraction pipelines with automated quality control for ML workflows.

Languages

PythonTypeScript / JavaScriptKotlinSQLBashC++

ML & LLM

PyTorchHugging Face TransformersvLLMFine-tuning & LoRARAGNGBoostSHAPTFT / TCNEvaluation & benchmarking

Agentic systems

MCP serversGoogle ADKAgent2Agent (A2A)gRPC / Protocol BuffersThompson Sampling routingTool-use design

Systems & infrastructure

KubernetesHelmKEDADockerSLURMGPU quota & node affinityNRP NautilusChameleon CloudAWS SageMaker / LambdaAzure Cosmos / SCOPEeBPF / strace / ptracePrometheus + Grafana

Web & data

Next.jsReactFastAPINode.jsPrismaSupabaseMongoDBPandas / NumPyGitHub Actions CI/CD