Built Breken, an AI support engineering platform that turns customer issues into root-cause investigations by correlating Zendesk tickets with Sentry, PostHog, infrastructure logs, and GitHub.

Designed a standardized observability layer that normalizes multi-source production data into a unified event model, enabling automated incident timelines, hypothesis generation, and RCA dossiers.

Built an agentic remediation workflow from support ticket to production evidence, root cause, human approval, and automatically generated GitHub fix PRs.

Architected ACL-aware retrieval and agent orchestration (Temporal, Kafka) for Brekfuz's enterprise knowledge agent across Slack, GitHub, Linear, Gmail, and internal memory.

Managed infrastructure with Terraform, Kubernetes, ECS/Fargate, and Redis; ran zero-downtime rollouts, guarded CI/CD, and production deployment safety checks.

Developed composable AI skills with the Mellea Skills Compiler for structured agentic application development.

Prototyped agent workflow patterns focused on reliability and reusable skill composition for enterprise agent systems.

Designed LLM retrieval pipelines over large co-occurrence corpora for adaptive product ideation pilots.

Implemented data pipelines combining structured food and formulation signals with semantic retrieval for R&D workflows.

Shipped an agentic coaching platform to 27K users and $200K ARR on Flask + TypeScript.

Redesigned core architecture, onboarding, and RevenueCat subscription systems; scaled to 5,850+ active customers and 532 trials.

Raised $500K from Airbnb's CMO, Credit Acceptance's CEO, and an a16z angel investor.

Developed Kubricks (React/TypeScript + Flask) with Celery/Redis pipelines for video ingestion, frame extraction, and Whisper transcription.

Ran SOTA vision-model training-data QA and evaluation against gold annotations to catch hallucinations and temporal errors.

Implemented Redis + TanStack Query caching for messaging, cutting DB reads and writes ~95%.

Developed in-app contract authoring and embedded signing so counterparties execute agreements in-product.

Implemented Congruence, an agentic EHR system supporting 20+ daily patients and therapist workflow orchestration.

Developed Flask pipelines for SOAP note generation and patient-context storage with LangChain, Redis, and Celery.

Architected TypeScript backend (Bun + Hono + Postgres) with multi-tenant data layer and tool-based agents over WebSocket streaming.

Scaled system to 4+ enterprise clients processing $2M+ GMV with extensible cross-tool automation; helped raise $1.0M seed.

Designed subgraph DAG + RAG pipeline (LangChain, QDrant), improving dietary recommendation accuracy by 22%.

Implemented LangGraph multi-step clinical reasoning (history, allergies, meal generation), reducing manual review time by 65%.

Developed ETL dashboard processing 120k+ clinical trial reports, cutting batch analysis from 4h to 45m (~80%).

Implemented semantic search with OpenAI embeddings + FAISS, improving R&D lookup productivity ~3x.

Optimized event-search queries and Redis caching, cutting API latency from 800ms to 120ms (~85%) under 500+ concurrent users.

Shipped React Native features (guest lists, RSVPs, discovery) used by 50k+ users with ~30% mobile performance gain.

Modeled ion-electron Coulomb drag coupling to predict open-circuit voltage and short-circuit current in Si nanochannels.

Designed CNT-integrated channel architectures targeting higher momentum transfer and energy harvesting efficiency.

Built subgraph DAG + RAG pipeline (LangChain, QDrant vector DB), improving dietary recommendation accuracy by 22%.

Collaborated with Food Network Chef James Briscione & White House Fellow Lav Varshney on clinical AI nutrition engine.

Built real-time React + Flask platform for multi-user LLM interaction research (40+ study subjects).

Ensured zero-loss message reliability via WebSockets + analytics logging for human-AI interaction experiments.

Integrated RL agent into MPC framework for autonomous EV routing in SUMO → improved control accuracy 25%.

Achieved 18% lower traffic delay in open-world simulations using ROS, C++, Python.

Analyzed experimental data and developed new concrete mixture by reducing clinker in cement.

Built Python + Random Forest models to predict composition impact on durability, reducing carbon emissions by 10%.

Held office hours and provided one-on-one support for students in computer science courses.

Graded assignments and provided detailed feedback to help students improve their programming skills.

Present technical presentations on hardware design, quantum computing, and machine learning applications in engineering.

Collaborate on circuitry and embedded systems projects with fellow IEEE members and technical communities.

Conducted market analysis and developed a go-to-market strategy for a new product line in the pipefitting industry.

Used NLP techniques to simplify complex insurance documents, making them more understandable for customers.

Developed and implemented a secure UART communication protocol for an embedded medical device.

Contributed to securing x86 architecture firmware by implementing memory-safe coding practices in Rust.

Built and styled responsive UI components for a cross-platform mobile app using React Native.

Translated Figma mockups into functional application screens and integrated them with a Python Flask backend.