KK

Kiran Kumar Ganaparapu

AI Engineer | Agentic AI & Gen AI | LangChain • LangGraph • CrewAI | Tool/Function Calling | LLMs • RAG • Fine-Tuning | AI Pipelines | Computer Vision • YOLO | Data Analytics | Python · Hyderabad, Telangana, India

As an Associate AI Engineer, I am driven by a logical and pragmatic approach, constantly seeking to master complex AI challenges. My ambition and creativity fuel my resourcefulness in developing innovative MLOps and advanced AI solutions, always striving for impactful and well-structured outcomes.

Open to

Hyderabad

Work style

onsite, remote, hybrid

Identity verified by DigiLocker
Contact details — on requestProof of Work — on request

Experience

B

Associate AI Engineer

Best Brains Inc · Feb 2025 – Present

Not yet confirmed
  • Building a Socratic AI tutor agent that teaches students by asking leading questions instead of giving direct answers — designed the agent's conversation flow, prompting strategy, and tool/function-calling loop (calculator for step-wise math verification, curriculum content retrieval, answer evaluation, hint generation).
  • • Built a RAG pipeline with semantic search, embeddings, and Crawl4AI-based web scraping for AI-ready content ingestion — grounding the tutor in curriculum content, improving factual accuracy and reducing hallucinations in production.
  • • Designed domain-specific LLM fine-tuning workflows using LoRA, QLoRA, and post-training quantization to adapt models to the tutoring domain while reducing inference cost.
  • • Curated training datasets from image sources using Gemini APIs and Tesseract OCR — selected after evaluating multiple local LLMs — reducing manual dataset-creation effort by ~75%.
  • • Integrated YOLO-based object detection to crop question regions with tables, graphs, and diagrams and map them to text — cutting manual cropping workload by ~70%.
  • • Automated the end-to-end data-preparation pipeline with Python (watchdog) — reducing manual workload by ~60%.
  • • Developed an internal LLM Gateway routing Claude, Gemini, and local LLMs (Ollama) with dynamic model selection, fallback handling, and cost optimization.
  • • Implemented LLM observability (latency, token usage, response quality) and refined evaluation workflows — improving downstream performance by ~25%.
A

Data Analysis & AI Intern

AJAI Robotics · Jul 2024 – Jan 2025

Not yet confirmed
  • Improved YOLO-based vision model performance by 10% through in-depth dataset analysis and optimization.
  • • Developed a voice-enabled AI system using Rasa for a smart coffee machine, increasing user interaction by 20%.
  • • Built a Flutter Android app with real-time visitor detection using MobileNet SSD — sensor-free customer identification triggering personalized welcome media, with Google Chat webhook notifications for entry logs and operational tracking.
  • • Deployed production Django + React applications with Gunicorn, NGINX reverse proxy, systemd services, and Let's Encrypt SSL — tuned workers and routing for near-100% uptime and low-latency performance.
  • • Contributed to computer vision model training and embedded-system integration for robots operating in real-world environments.
3

Data Science Intern

360DigiTMG · Nov 2023 – Apr 2024

Not yet confirmed
  • Proficient in Python, SQL, and Machine Learning: Developed strong skills in Python, SQL, and machine learning through hands-on projects and practical exercises.
  • Exploratory Data Analysis (EDA) & Visualization: Conducted in-depth EDA and created insightful visualizations using Python libraries like Pandas and Seaborn to uncover trends and patterns in datasets.
  • Collaborative Model Development: Worked on machine learning models, collaborating with the team to understand their real-world applications and improve model performance.

Skills 0 proven through work

Also works with

LabelMD UsageHard Negative MiningGapo Platform UsageDSPY Framework UsageRotational to Translational Motion ConversionAzure DeploymentGitHub ActionsCI/CD Pipeline ImplementationFeature EngineeringData PreprocessingFeature SelectionCorrelation AnalysisMachine Learning ApplicationSQL ProgrammingAutomated Control Systems ImplementationArduino ProgrammingHardware-Software IntegrationPython DevelopmentLLM Application IntegrationNatural Language UnderstandingRasa UsageCustom Voice Assistant DevelopmentPerformance Metrics AnalysisData OptimizationExploratory Data Analysis (EDA)Model Performance ImprovementComputer Vision ModelingData TransformationFile System ManagementImage CroppingYOLOv8 Model UsageModel Training ExecutionOCR System DevelopmentTesseract UsageGemini AI IntegrationTraining Data CreationNatural Language GenerationEmbedding GenerationSemantic SearchAI Agent Tool Usage MonitoringAI Model ConfigurationPrompt EngineeringData ValidationAPI IntegrationRetrieval-Augmented GenerationJSON Data HandlingData ModelingImage ProcessingConversational UX DesignAI Agent Development

Proof of Work

Proof of Work

Kiran shares this with people who ask. You'll hear back either way.

Education

Bachelor of Technology, Computer Engineering

Usha Rama College of Engineering & Technology,NH-5, Telaprolu, Near Gannavaram, Unguturu mandal, PIN- 521109.(CC-NG) · 2020 — 2024

Contact details

Contact details

Kiran shares this with people who ask. You'll hear back either way.

What drives their work

The Architect — Builds what holds

The Architect

They meticulously design and construct intelligent systems that are both functional and resilient.

Kiran's superpower

You excel at transforming complex requirements into structured, functional AI systems and optimizing their performance.

How Kiran works

You would thrive in a team focused on developing and optimizing intelligent systems, particularly those involving natural language processing, computer vision, or data-driven decision making.

Ask about this candidate

AI responses may contain errors. Proof status and source information are provided by Proof of Skill.

A Proof CV — one profile, kept current, with the proof attached. Back to the portal