Skip to content
View Anusha-raju's full-sized avatar
🎯
Focusing
🎯
Focusing

Organizations

@LAiSER-Software

Block or report Anusha-raju

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.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

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

Report abuse
Anusha-raju/README.md

Anusha Umashankar

Typing intro

Portfolio LinkedIn Email Washington, DC Open to Applied AI roles


👋 Hi, I'm Anusha

Three years of NLP and LLM work in production. These days that means LangGraph agents that call retrieval tools when they need them, plus the tracing and eval loop that tells me a change made things worse before a user does.

My habits: evals before features · a trace on every run · structured outputs instead of prompt warnings · cost and latency on the dashboard from day one.


🧭 How I build an agent

flowchart LR
    U([User query]) --> A{Agent<br/>LangGraph}
    A -- needs context --> R[(Hybrid retrieval<br/>BM25 + dense)]
    A -- needs fresh facts --> W[Web search tool]
    R --> A
    W --> A
    A --> S[Structured output<br/>schema-validated]
    S --> G{Eval gate<br/>groundedness · tool-call accuracy}
    G -- pass --> O([Answer + citations])
    G -- fail --> A
    A -.-> T[[Trace · cost · latency]]
Loading

🚀 Featured work

Hardened integrity checks for a decontamination pipeline covering 126K+ eval items and 7.8M n-gram fingerprints across 13 LLM benchmarks. Added a manifest-to-SHA-256 consistency check, a regression test, and 6 missing benchmarks to the registry.

Multi-agent clinical training platform. Each persona is its own LangGraph agent with a dedicated retriever, calling search_case_knowledge and web_search on demand. A ScopeAwareReferral schema makes scope of practice a structured output, not a prompt warning.

Privacy-first, fully offline RAG on Llama 3 via Ollama over a hand-written vector store. No API key and no egress, for runbooks and incident history that can't leave the building.

Graph-grounded RAG for automotive troubleshooting. A Neo4j graph captures part relationships that vector search misses, and hybrid retrieval with re-ranking handles domain terminology for multi-step diagnostic reasoning. Built in 48 hours at the DevNetwork AI+ML Hackathon.

More projects

💼 Experience

Instructional Technologist, AI/ML Infrastructure · GWU Data Science · Aug 2026 – Present
  • Building an advising assistant with hybrid dense + sparse retrieval grounded in program documentation, so students get cited answers instead of generic ones.
  • Run the AWS ML environments (EC2, S3, IAM, cost controls) for graduate capstone teams; containerized workspaces took setup from days to hours.
  • Scope and de-risk applied AI capstones with faculty and industry sponsors.
Research Assistant · LAiSER, GWU · Feb 2025 – May 2026
  • FAISS-based similarity search over 10,000+ job descriptions, mapped to the ESCO and O*NET skill taxonomies with a Neo4j graph for cross-taxonomy alignment.
  • Shipped it as a multi-tenant API on AWS (FastAPI, Lambda, S3, EC2) with Docker and GitHub Actions CI/CD: 3× research throughput, and time-to-demo from weeks to a live public product.
  • Presented the architecture to 150+ attendees at Badge Summit 2025.
Machine Learning Engineer · Ideapoke (now Chesz.ai) · May 2022 – Nov 2023
  • Rebuilt the NER pipeline behind Signalz, which turns news, patents and papers into market and technology signals: +40% extraction accuracy, −60% processing time.
  • Replaced brittle rule-based extraction with RAG (LangChain + GPT) producing structured output from large-scale unstructured web data.
  • Built a contextual search engine that retrieved on query intent rather than keyword match, across 30+ industries.

🔧 Toolbox

Core stack

Agents & retrieval LangGraph · LangChain · MCP · Hybrid retrieval (BM25 + dense) · Ollama · Neo4j · FAISS · pgvector
Evals & LLMOps LangSmith · Langfuse · RAGAS · LLM-as-Judge · Pytest
ML & NLP PyTorch · Hugging Face Transformers · scikit-learn · XGBoost · causal inference (IPTW)

🏅 Recognition & education

  • 🎤 Badge Summit 2025: presented "Skills Are the Common Language" to 150+ attendees.
  • 🛠 DevNetwork AI+ML Hackathon 2025: GearGuide, graph-powered RAG for automotive troubleshooting, in 48 hours.
  • 🌍 UN Open Source Hackathon 2025 · 🎮 HoyaHacks 2025 (Microsoft track) · 📊 World Bank DataDive 2024 with DataKind DC
  • 🌟 Global Leaders Scholarship, GWU (2024–25)
  • 🎓 M.S. Data Science, George Washington University (2026, GPA 3.91) · B.E. Computer Science, VTU Bengaluru

Footer

Pinned Loading

  1. era-v5-lab era-v5-lab Public

    Forked from theschoolofai/era-v5-lab

    ERA V5 training lab (The School of AI)

    Python

  2. GearGuidev2 GearGuidev2 Public

    GearGuide version 2 with hybrid search

    Python

  3. Human-Activity-Recognition Human-Activity-Recognition Public

    Python

  4. LAiSER-Software/extract-module LAiSER-Software/extract-module Public

    LAiSER is a tool that helps learners, educators and employers share trusted and mutually intelligible information about skills​.

    Python 11 8

  5. agentic-rag-support agentic-rag-support Public

    TypeScript 1

  6. marketing-intelligence-platform marketing-intelligence-platform Public

    End-to-end marketing ML platform for customer behavior analysis, conversion modeling, A/B testing, and causal inference using Olist e-commerce + marketing funnel data.

    Python 1