Skip to content
View aalva14's full-sized avatar
14 followers · 23 following

Achievements

Achievement: QuickdrawAchievement: YOLOAchievement: Arctic Code Vault ContributorAchievement: Pull Shark

Achievements

Achievement: QuickdrawAchievement: YOLOAchievement: Arctic Code Vault ContributorAchievement: Pull Shark

Block or report aalva14

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
aalva14/README.md

Hey, I'm Archana 👋

Lead Engineer building production agentic systems 🤖

I design and build the AI backend behind a RAG-based advisory platform

🔧 What I work on

  • Multi-agent architectures — LangGraph-based expert routing, management agents, and domain-specific sub-graphs
  • Retrieval pipelines — vector search (Qdrant), reciprocal rank fusion, reranking, multi-hop retrieval
  • Production AI infrastructure — async streaming (FastAPI + SSE), OpenTelemetry tracing, Azure OpenAI integration
  • Domain-driven AI — modelling complex legal and regulatory knowledge as navigable agent expertise

⚡ Tech

Python · FastAPI · LangGraph · LangChain · Qdrant · Azure OpenAI · PostgreSQL · Redis · OpenTelemetry · Docker

🔭 Currently exploring

  • Advanced retrieval strategies (multi-hop reasoning, adaptive chunking)
  • Agent evaluation frameworks and benchmarking
  • Cost-aware LLM orchestration patterns

🤝 Connect

LinkedIn

Pinned Loading

  1. Courseera_Applied_AI_with_DeepLearning Courseera_Applied_AI_with_DeepLearning Public

    Practice and assignments of Applied AI with DeepLearning course in course era

    Jupyter Notebook

  2. deep-learning-keras-tensorflow deep-learning-keras-tensorflow Public

    Forked from leriomaggio/deep-learning-keras-tensorflow

    Introduction to Deep Neural Networks with Keras and Tensorflow

    Jupyter Notebook

  3. gym gym Public

    Forked from openai/gym

    A toolkit for developing and comparing reinforcement learning algorithms.

    Python

  4. Image-OutPainting Image-OutPainting Public

    Forked from bendangnuksung/Image-OutPainting

    Keras Implementation of Painting outside the box

    Jupyter Notebook

  5. Keras-Tutorials Keras-Tutorials Public

    Forked from tgjeon/Keras-Tutorials

    Simple tutorials using Keras Framework

    Jupyter Notebook

  6. stanford_dl_ex stanford_dl_ex Public

    Forked from amaas/stanford_dl_ex

    Programming exercises for the Stanford Unsupervised Feature Learning and Deep Learning Tutorial

    MATLAB