Open to AI Engineer opportunities

AI Engineer.

Building intelligent systems with LLMs, RAG, and agentic architectures

Talk to my AIView Projects
3+
Years Experience
5+
AI Projects
90%
Agent Accuracy

Featured Projects

Personal AI projects showcasing expertise in LLMs, RAG, and agentic architectures

FinAgent - Autonomous Financial Analysis Agent

AI-powered financial analyst leveraging the ReAct pattern for autonomous tool selection and real-time analysis.

FinAgent is an autonomous financial analyst that uses the ReAct (Reasoning + Acting) pattern to answer investment and financial queries. It autonomously selects appropriate tools, executes them, and delivers transparent, evidence-based responses. The system handles complex queries requiring multiple data sources through natural language interaction, providing real-time financial insights.

Key Features

  • •Autonomous tool selection using ReAct pattern (Reasoning + Acting)
  • •Real-time streaming with Server-Sent Events (SSE)
  • •Comprehensive evaluation: tool selection accuracy, parameter extraction, response grounding
  • •Multi-step query handling with transparent reasoning process
  • •Stock price lookup (historical and current)
  • •Company information retrieval
  • •Financial ratio calculations (P/E, ROE, ROA, margins)
  • •Investment return projections

Highlights

  • ✓Demonstrates agentic architecture with autonomous decision-making
  • ✓Real-time reasoning transparency for explainable AI
  • ✓Production-ready evaluation metrics for quality assurance
  • ✓Full-stack implementation with modern tech stack

Technology Stack

FastAPIReact 18TypeScriptOpenAI GPTPydanticyfinanceViteTailwind CSSRecharts

JudRag - Legal Document RAG System

Retrieval-augmented generation system for semantic search over legal documents and case law.

JudRag is a specialized RAG (Retrieval-Augmented Generation) system designed for legal documents. It enables semantic search over judicial documents, case law, and statutes using vector embeddings and conversational interfaces. The system preprocesses legal documents into chunked text, stores them in a vector database, and provides conversational search capabilities for legal professionals.

Key Features

  • •Semantic search over legal documents using vector embeddings
  • •RAG pipeline with Chroma vector database
  • •Conversational interface for case law queries
  • •Document chunking and preprocessing for optimal retrieval
  • •Session management for conversation history
  • •Full-text search combined with semantic similarity

Highlights

  • ✓Demonstrates RAG expertise with domain-specific application
  • ✓Combines traditional search with modern LLM capabilities
  • ✓Full-stack implementation from data processing to UI
  • ✓Specialized for legal/judicial domain knowledge

Technology Stack

FastAPIFlaskChromaPythonVector SearchHTML/CSS

Experience

Professional journey in AI engineering and software development

Work Experience

AI Engineer

Strategy (Formerly MicroStrategy)
July 2024 - Present•Tysons, VA
  • •Led development of flagship AI products "Agents" and "Auto Dashboards" from concept to release, collaborating across product, delivery, and engineering teams
  • •Designed the Agent system, enabling users to create custom AI agents from structured and unstructured data to answer analytical questions with ~90% accuracy
  • •Architected a multi-provider AI layer, supporting seamless integration and switching between OpenAI, Gemini, and Claude for dynamic inference routing
  • •Architected a semi-orchestrated deterministic flow for the Auto Dashboard system — transforming natural-language intent into fully formatted dashboards within seconds, cutting dashboard creation time by over 95%
  • •Led a cross-functional team to develop a central prompt library, standardizing and optimizing all prompt templates used across enterprise AI applications
PythonTypeScriptOpenAIGeminiClaudeRAGPrompt EngineeringLangChain

Data Scientist (Internship)

Strategy (Formerly MicroStrategy)
July 2023 - May 2024•Tysons, VA
  • •Developed Auto Expert, a publicly available RAG-based AI assistant for Strategy Software that helps customers find product information, troubleshoot issues, and access community resources, leading to a 20% reduction in customer support cases through automated case deflection
  • •Implemented machine learning guardrails and hallucination reduction algorithms before guardrail frameworks were mature, achieving a 10% improvement in factual accuracy
  • •Created a user-friendly tester UI using React and Node, leading to a 30% boost in testing efficiency among project testers while smoothly integrating and optimizing data flow into a separate database, reducing data access time by 40% during testing
RAGReactNode.jsPythonVector SearchLLMs

Software Development Engineer

Rupeek Fintech
January 2022 - August 2022•Bengaluru, India
  • •Designed a multi-app platform for the autonomous lending of gold loans using Node.js, React, Electron.js, and TypeScript
  • •Created and managed app development by implementing scalable backend and frontend for customer-facing products
  • •Impacted the loan dispersal process, resulting in $122K disbursed to over 1000 customers, opening new revenue sources
  • •Collaborated across teams to identify business requirements and execute scalable solutions, improving client-server interactions by reducing API latency by 1 second
Node.jsReactElectron.jsTypeScriptPostgreSQL

Education

Master of Science in Computer Science

The George Washington University
May 2024•Washington, DC

Relevant Coursework:

Computer Architecture, Big Data and AI, Machine Learning, Cloud Computing, Database

Bachelor of Engineering

Thapar Institute of Engineering and Technology
June 2021•Patiala, India

Relevant Coursework:

Data Structures and Algorithms, Artificial Intelligence, Digital Image Processing

Technical Skills

Comprehensive toolkit for building cutting-edge AI systems

AI/ML

Large Language Models (LLMs)Retrieval-Augmented Generation (RAG)Prompt EngineeringAgentic ArchitecturesModel Context Protocol (MCP)LangChainLangGraphSemantic RetrievalVector DatabasesGenerative AIOrchestration

Languages & Frameworks

PythonTypeScriptJavaScriptSQLReact.jsNext.jsNode.jsFastAPIDjangoFlaskPydantic

Data & Infrastructure

PostgreSQLMongoDBRedisSparkKafkaRedshiftAirflowHadoopAWSAzureDockerKubernetes

Tools & Technologies

GitLinuxTableauData ModelingMapReduceScalaMATLAB

Get in Touch

Interested in discussing AI engineering opportunities or collaborations?

Contact Information

[email protected]linkedin.com/in/satkalragithub.com/satkalra

Currently Seeking

AI Engineer roles focusing on LLMs, RAG systems, and agentic architectures. Open to full-time opportunities in the United States.

Chat with my AI

Ask me anything about my experience, projects, and skills

Coming Soon

The RAG-powered chatbot is currently being fine-tuned and will be available soon. In the meantime, feel free to reach out via the contact section!

What to expect: An intelligent AI assistant that can answer questions about my experience with RAG systems, LLMs, agentic architectures, and all my projects in detail.