Skip to content
View abhay-lal's full-sized avatar
πŸ’»
πŸ’»

Highlights

  • Pro

Organizations

@srm-mic @Data-Science-Community-SRM @Codificacion-Circulo

Block or report abhay-lal

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
abhay-lal/README.md

Hi, I’m Abhay Lal

MS CS (AI) @ UC San Diego | ML + GenAI Engineer πŸ€– | Building agentic systems, multimodal ML, and healthcare AI 🌱

Profile Views


πŸ§‘β€πŸ’» About Me

πŸŽ“ MS in Computer Science & Engineering (2024–2026) at UC San Diego
🧠 Graduate Researcher @ UCSD Health building multimodal ML pipelines (imaging + genetics + clinical data) + explainability (SHAP/XAI)
πŸ€– I like shipping GenAI systems: RAG, tool-calling agents, eval/guardrails, and graph-backed workflows
🌱 Exploring LLM post-training, RL for LMs, TinyML, and mixed-effects modeling
🎯 Open to collaborations + 2026 full-time roles (MLE / Applied AI / GenAI)


πŸ› οΈ Skills

Languages

ML / DL

GenAI / Agents

Data / Visualization

Backend / Infra

Databases

Tools

πŸš€ Featured Projects

  • BlogPod: Podcast β†’ structured blogs using LLMs + RAG, with retrieval, citations, and eval hooks
  • MusiCRS: Conversational Music Recommendation benchmark + pipeline (entities, grounding, reproducibility)
  • Visper: Voice-first RAG assistant for GitHub repos (chunking, retrieval, tool-calling workflows)
  • AI Safety Protocol: Guardrails + eval suite for agentic systems (policy checks, red-team tests, reliability metrics)
  • Owl Vocalization Detection Collar: TinyML model on microcontroller for real-time burrowing owl call classification
  • Fire-Ready Forests Challenge πŸ† Hackathon Winner: Hierarchical ensemble pipeline for vegetation/tree classification in fire-prone ecosystems
  • Asset Bubble πŸ† Hackathon Winner: Market crash prediction app with end-to-end modeling + dashboarding

πŸ“š Publications

  • Automated Screening of Hip X-rays for Osteoporosis Using Machine Learning, Indian Journal of Orthopaedics (2024)
  • Human Gait Recognition Using Cross-View Datasets with MobileNet, IEEE Xplore (2023)
  • Gait Speed Based Individual Recognition Model using Deep 2-D CNN, IEEE Xplore (2023)

πŸ“ˆ GitHub Stats

GitHub Stats GitHub Streak

πŸ“« Connect with Me

LinkedIn Gmail Website X


⚑ Fun Fact I built systems that classify owl calls on-device, and I’ve also trained models to generate music 🎼

Pinned Loading

  1. Alveoli Alveoli Public

    Chest X-Ray reports in a matter of seconds.We have created a secure Chest X-Ray image classification based website and app that can detect Covid-19, Pneumonia and Tuberculosis. Deep Learning has be…

    Jupyter Notebook 3

  2. Asset-bubble Asset-bubble Public

    Project helps the investors using a predictive analytics model or providing actionable analytical insights to this problem. The output is the confidence score on whether the stock market will crash…

    Jupyter Notebook 4

  3. AI-safety-protocol AI-safety-protocol Public

    Advanced four-layer AI-powered guardrails for multi-agent systems designed to prevent destructive behaviors in large language models (LLMs). The framework includes prompt validation, backdoor attac…

    TypeScript

  4. fire-ready-forests-agni fire-ready-forests-agni Public

    Jupyter Notebook 3

  5. TinyML-Owl TinyML-Owl Public

    C

  6. Visper Visper Public

    Visper is a voice-first RAG assistant for your repositories. Paste a GitHub URL and talk to your code in real time answers are grounded with citations and links back to files. Visper can also turn …

    Python