CS Junior · Arizona State University · 4.0 GPA

Builds
software.
Ships AI.

FULL-STACK · AI/ML
DATA SYSTEMS ENGINEER

Full-stack SaaS
(OfferKite, 50 beta testers).

LLM evaluation harness
(Egnyte, 200+ test scenarios).

Ontology modeling + SQL optimization
(Palantir, 93% accuracy, 4.2s → 2.1s).

Data pipelines + statistical agents
(Sala Lab, 325+ quality flags).

8 production agentic systems
(ASU, $40K annual savings).

Versatile software engineer with 1.5+ years of experience building shipped systems across full-stack, AI/ML, and data domains.

Built a full-stack SaaS currently in beta with 50+ active testers, built automated LLM evaluation pipelines at Egnyte covering 200+ test scenarios which cut manual testing time by ~60% and improved agent model accuracy by 35%, modeled ontologies and optimized query performance at Palantir achieving 93% accuracy and cutting latency from 4.2s to 2.1s, engineered data pipelines and statistical agents at Sala Lab that flagged 325+ quality issues before downstream processing, and deployed 8 production agentic systems at ASU generating $40K in annual savings.

Looking for a SWE or AI/ML internship focused on shipped, production-grade systems.

0
Production agentic workflows deployed live for small-mid scale businesses via Aevron
0+
Waitlist signups with 50+ active beta testers on OfferKite SaaS
0%
Manual evaluation time cut through automated LLM testing workflows at Egnyte
0+
Images preprocessed and augmented via torchvision, reducing batch processing from 3 hours to fully automated
0+
Data quality issues flagged by statistical agents before reaching downstream models at Sala Lab
0
Production-grade agentic systems deployed at ASU, saving $40K annually and 70-150 hours per week at peak

Four teams. One pattern: identify the friction, engineer the system, ship it at scale.

Software Engineer, Agentic Systems
Arizona State University · IEM

Built 8 Python agentic systems (Selenium, pandas, openpyxl, Outlook API) executing I-9 and immigration workflows across Workday, Equifax, and Sprintax.

Cut processing time from 1–3 hours to under 5 minutes per task, saving ~28 hrs/week and up to ~40 hrs/week during peak periods.

Built an Outlook-integrated email agent (Python + Microsoft Graph API + rule-based classification) that reads I-9/immigration inbox emails, classifies queries, pulls employee data, and replies without manual intervention.

Delivered ~$40K in annual savings and wrote documentation that lets non-technical staff run and troubleshoot the systems themselves.

OCT 2025 – PRESENT
Research Engineer
Sala Lab

Built ingestion and validation pipelines in Python and R across field and sensor data sources, cutting manual cleaning time by ~30 hours per week.

Developed statistical agents that automatically flag missing values and anomalous sensor readings, catching 325+ data quality issues before they reached downstream models.

Set up computer vision preprocessing with torchvision to standardize and augment ecological image data, taking preprocessing from ~3 hours per batch to fully automated across 25,000+ images.

JAN 2026 – MAY 2026
Software Engineering Intern
Egnyte

Designed and ran evaluation suites covering 200+ test scenarios to measure AI agent accuracy, response quality, and edge-case behavior.

Built automated LLM testing workflows with batched, parallelized execution, cutting manual evaluation time by ~60%.

Constructed benchmark datasets that surfaced failure modes feeding directly into model improvement cycles, improving total test coverage by 35%.

Presented evaluation findings and coverage gaps to the agent team in weekly syncs.

JUL 2025 – AUG 2025
Research Assistant
IIT BHU

Built multi-granularity datasets (daily, weekly, monthly) from 5 years of raw time series data, engineering features to surface trend, seasonality, and autocorrelation.

Trained and benchmarked ARIMA, Prophet, XGBoost, and LSTM; XGBoost outperformed by 18% on RMSE (weekly granularity), later adopted into the team's production pipeline.

Shipped a resampling frequency analysis that cut the team's trial-and-error preprocessing time by ~5 hours per experiment.

MAY 2025 – AUG 2025

Things I built on my own time because I wanted them to exist.

  • Built a full-stack job-hunt SaaS: Sam aggregates roles from GitHub sources, ranks them by rule-based scoring (role fit, location, visa, company stage, recency), and tracks applications with recruiter outreach.
  • Engineered apply-core as a universal form-fill engine with computer-vision fallback for unsupported portals; the same DOM-inspection and field-resolution code runs in both the Chrome extension (production) and Playwright (testing/CI).
  • Architected Rosie's automation as server-orchestrated browser control: the server handles LLM planning, RemotePlanner directs the extension to fill forms in a real browser (cookies, SSO, CAPTCHA pauses, file uploads), session sync keeps state consistent across layers.
  • Shipped to live beta with 50 active testers and 500+ waitlist signups, actively iterating on fill resilience, Workday expansion, and cross-device persistence.
  • Built and operate a services business designing and shipping production agentic systems and custom web applications for local businesses and startups; own the full lifecycle from requirements mapping to deployment, monitoring, and ongoing iteration.
  • Deployed 4+ production workflows handling invoicing, follow-ups, lead routing, inventory sync, and reporting, designed for reliable operation under real volume and edge cases, with error handling, logging, and observability built in from day one.
  • Architect agentic workflows that automate operational tasks (triage, routing, communications) with guardrails and human oversight, integrating across existing client tools to eliminate manual re-keying and create single-source-of-truth dashboards.
  • Operate with accountability for outcomes, not hype; measure success by reduced manual steps and operational friction, positioned for transition to recurring agentic automation retainers.

Things I built because I wanted to know if they'd actually work.

01
Phantom A100
CUDA Attention Optimization & GPU Performance Engineering
  • Engineered 6 CUDA attention kernel variants, implementing shared-memory tiling, online-softmax fusion, vectorized memory access, asynchronous double buffering, and Tensor Core acceleration.
  • Achieved a 57.9× simulated speedup over naive attention using Tensor Core WMMA kernels, identifying memory bottlenecks, register pressure, and GPU occupancy constraints.
  • Built a counter-guided autotuning system that analyzes GPU performance metrics, selects kernel transformations, and validates optimization decisions against predicted hardware behavior.
  • Validated 23 kernel configurations on a real NVIDIA A100, achieving 0.800 Spearman ranking correlation between simulated and measured performance, with the Tensor Core variant ranking fastest.
  • Debugged and patched 5 GPU simulator defects involving Tensor Core emulation, warp shuffles, and instruction latency, enabling reliable correctness testing and architectural analysis.
CUDA C++ Python PyTorch GPGPU-Sim NVIDIA A100 Tensor Cores WMMA
02
PocketVLM
Vision-Language Model Compression & On-Device AI
  • Built an end-to-end vision-language model compression pipeline, fine-tuning Qwen2.5-VL-3B on VQAv2 and evaluating quantization, LoRA, QLoRA, and knowledge distillation.
  • Compressed a 7.51 GB model to 1.54 GB (4.9× smaller) while retaining 97.6% of baseline VQA accuracy through teacher-student distillation and GGUF quantization.
  • Achieved 41.6 decode tokens/sec and 2.69-second end-to-end inference latency per image question on a 16 GB MacBook Air M3 using llama.cpp and Metal.
  • Benchmarked GPTQ, AWQ, and GGUF across multiple precision levels, measuring accuracy, memory footprint, and inference speed to identify practical compression tradeoffs.
  • Developed reproducible training and evaluation pipelines with cross-backend validation, automated reporting, and a fully local browser demo for image-based question answering.
Python PyTorch Hugging Face LoRA QLoRA GPTQ AWQ GGUF llama.cpp vLLM Apple Metal
03
Meshwork
Distributed LLM Training & GPU Scaling
  • Built a distributed LLM training system using PyTorch DDP and FSDP2, benchmarking GPT models across 1, 2, and 4 NVIDIA H100 GPUs.
  • Achieved 92.5% weak-scaling efficiency and 933K tokens/sec with DDP on 4 GPUs, measuring training throughput, synchronization overhead, and GPU utilization.
  • Reduced per-GPU model-state memory by 75% using FSDP2 sharding, enabling training of 12.85B-parameter models, 4.85× larger than the largest tested DDP configuration.
  • Optimized distributed training with bf16 mixed precision, fused AdamW, and NCCL collectives, improving FSDP training step performance by 1.8×.
  • Developed reproducible GPU benchmarks, memory profiling, communication analysis, and correctness tests to identify bottlenecks in distributed training.
Python PyTorch CUDA NCCL DDP FSDP2 NVIDIA H100
04
AgentBench
LangChain Agent Evaluation Harness
  • Architected a full-stack evaluation harness for LangChain tool-using agents: trajectory interception (DAG capture of tool calls, args, outputs, latency), parallel multi-metric scoring, and regression detection against rolling history.
  • Built a non-invasive LangChain tool wrapper that intercepts every agent decision point, recording it as a DAG node with reasoning traces, token counts, and parent-child links to reconstruct the full decision trajectory.
  • Designed three concurrent scoring metrics to catch failures end-to-end answer checks miss: tool-call accuracy (Levenshtein distance), semantic similarity (sentence-transformer embeddings), and faithfulness (claim grounding).
  • Implemented z-score regression detection against a rolling 30-run history, flagging quality degradation as small as 1.5σ before it cascades into production.
  • Shipped SQLite persistence (four-table schema) plus a Streamlit dashboard with KPI strips, pass-rate bars, metric distributions, and full trajectory replay, all local, no external services.
LangChain SQLite Streamlit
05
Public Defender Intelligence System
Palantir Foundry / AIP
  • Built a six-object ontology with four link types from six synthetic datasets, then architected six agentic workflows grounded directly in it.
  • Chose SQL-over-ontology retrieval instead of embeddings, since exact case_ID matches mattered more than semantic recall.
  • Root-caused a grounding failure to an unscoped case_ID, fixed it, and hit 93% grounding accuracy on a 15-case held-out test set.
  • Cut response latency 4.2s → 2.1s by trimming the input payload to deal-relevant fields only.
Foundry AIP Logic SQL
06
Context-Aware AI Chatbot
RAG Architecture
  • Built a RAG chatbot with OpenAI + LangChain, handling ingestion, chunking, and FAISS vector embeddings from scratch.
  • Cut irrelevant retrieval by 20% and latency from ~4s to under 1.5s through optimized chunking and prompt engineering.
  • Deployed to 100+ users over a 2-week live beta with 98%+ uptime.
LangChain FAISS Streamlit
07
ScanTaps
EPICS Community Service
  • Built computer-vision tag fallback reducing manual photo-matching time by 85%, enabling recovery of ~60% of items with missing/damaged NFC tags.
  • Built a React + Firebase lost-and-found platform mapping NFC/QR tags to dynamic, Firestore-backed recovery pages.
  • Built an admin dashboard with search, filters, pagination, record stats, and CSV export.
React Firebase torchvision

The stack, end to end.

CUDACUDA C++NCCLPyTorch DDPFSDP2GPGPU-SimNVIDIA A100NVIDIA H100Tensor CoresWMMAGPU ProfilingDistributed Training
PyTorchHugging FaceLangChainOpenAI APIscikit-learntorchvisionRAGFAISSComputer VisionVision-Language ModelsAgentic WorkflowsPrompt Engineering
llama.cppvLLMGGUFGPTQAWQLoRAQLoRAKnowledge DistillationModel QuantizationKernel FusionMixed-Precision TrainingApple Metal
PythonCC++JavaJavaScriptTypeScriptSQLRHTMLCSS
pandasNumPyXGBoostLSTMARIMAProphetData PipelinesData ValidationTime Series ForecastingStatistical AnalysisPower BITableau
FastAPIPostgreSQLSQLiteFirebaseFirestorePrismaREST APIsAWSAzureMicrosoft Graph APIPalantir FoundryPalantir AIP
ReactNext.jsStreamlitSeleniumPlaywrightChrome ExtensionsBrowser AutomationWorkflow AutomationDOM InspectionAPI IntegrationMicrosoft Outlookopenpyxl
GitGitHubDockerLinuxJupyterVS CodepytestCI/CDEvaluation PipelinesRegression TestingPerformance BenchmarkingMicrosoft Excel

Foundations.

Arizona State University
B.S. Computer Science · Minor in Data Science · Minor in Statistics
Awards: New American University Scholarship, Dean's List (2024–2026)
Coursework: Data Structures & Algorithms, Computer Systems, Probability, Applied Statistics, Database Systems
4.00
GPA