Skip to content
View selvakumarperumal's full-sized avatar

Block or report selvakumarperumal

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
selvakumarperumal/README.md

Selvakumar Perumal

Building AI-powered applications from prototype to production.
Specializing in voice agents, multi-agent systems, and real-time RAG pipelines.


$ cat whoami.py

class SelvakumarPerumal:
    """I don't just build AI.  I ship it."""
    
    def __init__(self):
        self.role = "ML/AI Developer | AI Systems Architect"
        
    @property
    def current_obsessions(self) -> dict:
        return {
            "voice_agents": "Voice that thinks before it speaks",
            "multi_agent":  "Agents that actually cooperate",
            "rag_systems":  "No more hallucinations, only facts",
            "mlops":        "Ship it, scale it, sleep"
        }
    
    def hire_me(self) -> bool:
        return True  # Always returns True
    
    def say_hi(self) -> str:
        return "Wanna build something mass together?"

$ cat tech_stack.yaml

ai_ml: 
  deep_learning:        [PyTorch, HuggingFace, OpenCV, spaCy]
  llm_frameworks:       [LangChain, Haystack]
  agent_orchestration:   [LangGraph, Pydantic-AI, Pydantic-Graph]
  classical_ml:         [Scikit-learn, XGBoost]

backend:
  framework:            [FastAPI, Pydantic, SQLModel, SQLAlchemy]
  databases:            [PostgreSQL, MongoDB, Redis]
  data_processing:      [Pandas, Polars, NumPy]

infrastructure:
  containers:           [Docker, Kubernetes, Helm, Istio]
  cloud:                [AWS, Terraform]
  monitoring:           [Prometheus, Grafana, EFK Stack]
  ci_cd:                [GitHub Actions]

protocols:              [REST, GraphQL, WebSocket, WebRTC, MQTT, LiveKit]

environment:
  os:                   Linux
  shell:                [bash]

$ github stats


Prototype start. Production end. Adhuku naduvula magic.

Pinned Loading

  1. AML_Policy_FAQ_BOT AML_Policy_FAQ_BOT Public

    Build a chatbot that answers compliance officers’ Anti-Money Laundering (AML) questions by retrieving relevant internal AML policy documents and using an LLM to generate context-aware responses.

    Python

  2. Anti_Money_Laundering_report_auto_filter_agent Anti_Money_Laundering_report_auto_filter_agent Public

    Jupyter Notebook

  3. Corporate_Filing_Analyzer_Agent Corporate_Filing_Analyzer_Agent Public

    Jupyter Notebook

  4. Customer_Complaint_Responder Customer_Complaint_Responder Public

    Jupyter Notebook

  5. FinTech-Compliance-Document-Simplifier FinTech-Compliance-Document-Simplifier Public

    Easily simplify complex financial compliance documents using AI! Upload PDF/DOCX/TXT files and get plain-language summaries using GPT via LangChain — all powered by FastAPI, Celery, and Redis.

    Python

  6. credit-risk-underwriting-assistant credit-risk-underwriting-assistant Public

    AI-assisted underwriting tool for streamlined credit risk assessment.

    HCL