Sala Tendool Srivatsav

AI/ML & Data Engineer — agentic systems, data pipelines & applied deep learning

I build AI thathas to workoutside the notebook.

Agents, vision systems and small language models, and the data pipelines underneath them — taken all the way to the device in someone’s hand. Currently an AI intern at Yitro Global, and finishing a B.Tech in AI & Data Science.

Now
AI Intern, Yitro Globalsince Sep 2025
Studying
B.Tech, AI & Data ScienceASE Coimbatore · 2027
Based in
Bobbili, Andhra Pradesh local time
Open to
AI/ML & data engineering rolesAvailable now

Selected work

6 of 20 — the rest are in the index

01

Agentic HR query resolution

Yitro Global · client work · 2026 — now

Three cooperating agents — data extraction, knowledge search and voice analytics — answer employees’ HR questions, grounded in the company’s own policy documents through fine-tuning and retrieval-augmented generation.

3 agentsone shared, policy-grounded knowledge base

LLMs · Fine-Tuning · RAG · Python

Details in the index
02

TARA, a voice assistant that never phones home

Personal · 2026 — now

Wake word, speech-to-text, a local language model that can call tools, and speech synthesis — openWakeWord, faster-whisper, Qwen and Piper wired into one loop that runs entirely on the machine in front of you.

0cloud services anywhere in the loop

Python · Ollama · SLM · ASR · TTS

Details in the index
03

SLM-driven adaptive tutoring agent

Yitro Global · client work · 2026 — now

A self-paced learning agent that tailors what it teaches, how fast and how hard to each learner’s progress, grounded with retrieval-augmented generation — and talks the lesson through, using CUDA-accelerated inference and text-to-speech to keep the voice low-latency.

3things it adapts per learner: content, pacing and difficulty

SLM · CUDA · TTS · RAG

Details in the index
04

SmartSight, guidance from a phone camera

University · 2025 — now

A navigation assistant for visually impaired users: real-time obstacle detection and spoken, hands-free guidance, using object detection and speech recognition on the phone they already carry.

1 camerathe phone’s own — no external hardware

Deep Learning · Android Studio · OpenCV · ASR · Jetson Nano

Details in the index
05

Quantum ML for multimodal disease prediction

University · 2025

Quantum neural networks, variational quantum classifiers and hybrid classical–quantum models built in Qiskit and TensorFlow, then measured against the classical models a clinician would actually reach for.

~87%accuracy, with better recall than RF, SVM and MLP

Qiskit · TensorFlow · QNN · VQC

Details in the index
06

Prescription validation on HDFS

University · 2025

A distributed big-data pipeline on HDFS that processes patient prescription data at scale, feeding a machine-learning validation engine that warns patients on several prescriptions about unsafe drug combinations.

Real-timeflags for unsafe drug combinations

AWS · Machine Learning · HDFS · Python

Details in the index

Experience

Yitro Global

AI Intern — AI Algorithms for Enterprise Systems

Sep 2025 — present · Remote

  1. i.

    SLM-driven tutoring application

    Engineered an AI tutoring application driven by a small language model, with an interactive agent avatar delivering real-time explanations, quizzes and hands-on coding feedback — alongside a teacher-facing analytics and classroom-management dashboard.

  2. ii.

    Enterprise talent-matching network

    Architected a talent-matching network on graph databases and multi-agent orchestration, helping recruiters find the best candidate-to-role fits through clan-based clustering.

  3. iii.

    Agentic CRM platform

    Built an end-to-end CRM platform and designed LLM-driven chatbots that agentize its workflows, automating lead management and customer interactions.

  4. iv.

    Recruiter–job seeker matching app

    Developed a recruiter–job seeker matching application that uses graph-based clan clustering to improve candidate discovery and engagement.

  5. v.

    Multi-agent enterprise retrieval

    Designed a multi-agent system — a knowledge-based search agent, a data extraction agent and a voice agent — to automate enterprise information retrieval and query resolution.

Also on the record: NVIDIA RTX AI PC Day, Jan 2026

Index of projects

    • Built an end-to-end voice assistant that runs entirely on-device — wake word detection, speech-to-text, a local language model with tool use, and speech synthesis — with no cloud service anywhere in the loop.
    • Wired openWakeWord, faster-whisper, a locally served Qwen model and Piper TTS into a single tool-calling loop, verifying each stage round-trip against real microphone input rather than mocking it.
    Period
    Sep 2026 — Present
    Stack
    Python, Ollama, SLM, ASR, TTS
    • A personal mobile assistant application, currently in active development.
    Period
    Sep 2026 — Present
    Stack
    Mobile, Assistant
    • Designed and built this site: an editorial layout whose figures are live WebGL scenes, all drawn through a single shared canvas and shaded by one ordered-dither shader so they print like 1-bit illustrations.
    • Every figure is lit from wherever the cursor is, and is assembled from primitives in code — there are no model or texture files.
    Period
    Sep 2026 — Present
    Stack
    Next.js, React Three Fiber, GLSL, TypeScript
    • Built a conversational agent answering founder-level business questions from two live project-management boards, reconciling a client-code mismatch that turned out to be the real cross-board join key and discarding corrupted rows that would otherwise have silently broken every cross-board metric.
    • Wrote and unit-tested the cleaning, normalisation and analytics tools against the real data with no model in the loop, so the agent only had to call verified tools correctly and surface their caveats rather than do the arithmetic itself.
    Period
    Aug 2026
    Stack
    Python, React, Docker, LLM Tool Use
    • An AI-powered tutoring application driven by a Small Language Model, with an interactive agent avatar delivering real-time explanations, quizzes and hands-on coding feedback, plus a teacher-facing analytics and classroom management dashboard.
    • Built a self-paced learning agent that dynamically tailors content, pacing and difficulty to each learner’s progress using RAG-grounded content retrieval.
    • Leveraged CUDA-accelerated inference and Text-to-Speech to deliver low-latency, voice-interactive tutoring sessions.
    Period
    Feb 2026 — Present
    Stack
    SLM, CUDA, TTS, RAG
    Note
    Client project — internal name withheld.
    • Designed a multi-agent architecture combining a data extraction agent, a knowledge-based search agent for automated HR query clarification, and a voice analytics agent for conversational insight generation.
    • Applied LLM fine-tuning and Retrieval-Augmented Generation to ground responses in company-specific HR policy data, improving answer accuracy and reducing manual HR ticket resolution time.
    Period
    Jan 2026 — Present
    Stack
    LLMs, Fine-Tuning, RAG, Python
    Note
    Client project — internal name withheld.
    • Built a multi-agent orchestration platform combining LLMs, SLMs and local models for enterprise agentic workflows.
    Period
    Dec 2025 — Feb 2026
    Stack
    Python, CUDA, RAG, LLMs, SLMs
    Note
    Client project — internal name withheld.
    • Built a smartphone-based navigation assistant for visually impaired users, delivering real-time obstacle detection and interactive voice guidance using only the device’s built-in camera — no external hardware required.
    • Integrated deep learning-based object detection with Automatic Speech Recognition to create a hands-free, voice-interactive navigation experience.
    Period
    Nov 2025 — Present
    Stack
    Deep Learning, Android Studio, OpenCV, ASR, Jetson Nano
    • Developed predictive ML pipelines and intelligent energy management models to optimise Solid Oxide Electrolysis Cell performance and efficiency for green hydrogen production.
    Period
    Nov 2025 — Present
    Stack
    Machine Learning, Predictive Modeling, Energy Systems
    • Built an end-to-end CRM platform and designed LLM-driven chatbots to agentize CRM workflows, automating lead management and customer interactions.
    Period
    Sep 2025 — Present
    Stack
    LLMs, Chatbots, Agentic AI, CRM
    Note
    Client project — internal name withheld.
    • Architected an enterprise talent-matching network using graph databases and multi-agent orchestration, enabling recruiters to identify optimal candidate-role fits through clan-based clustering.
    Period
    Sep 2025 — Present
    Stack
    Graph DB, Multi-Agent, Clustering
    Note
    Client project — internal name withheld.
    • Developed a recruiter–job seeker matching application leveraging graph-based clan clustering to improve candidate discovery and engagement.
    Period
    Sep 2025 — Present
    Stack
    Graph DB, Clustering
    Note
    Client project — internal name withheld.
    • Built Quantum Neural Network, Variational Quantum Classifier and hybrid classical-quantum models using Qiskit and TensorFlow.
    • Achieved ~87% prediction accuracy with improved recall and sensitivity versus classical baselines (Random Forest, SVM, MLP).
    Period
    Jun 2025 — Oct 2025
    Stack
    Qiskit, TensorFlow, QNN, VQC
    • Built a distributed big data pipeline on HDFS to process patient prescription data at scale.
    • Developed a machine learning-based validation engine that flags unsafe drug combinations in real time for patients managing multiple prescriptions, improving prescription safety.
    Period
    Jun 2025 — Oct 2025
    Stack
    AWS, Machine Learning, HDFS, Python
    • Developed a robotic hand that mimics user hand gestures in real time using deep learning and OpenCV on Raspberry Pi.
    Period
    Jun 2025 — Oct 2025
    Stack
    Deep Learning, OpenCV, Robotics, Raspberry Pi, Python
    • Developed a machine learning-based crop disease identification tool enabling farmers to diagnose plant health issues from images.
    • Built a marketplace module for farmers to buy and sell agricultural machinery and equipment, and delivered personalised fertiliser and crop-care recommendations based on real-time crop and soil status.
    Period
    Dec 2024 — Apr 2025
    Stack
    Machine Learning, AWS, HTML, Java, CSS
    • Built a lane detection and text recognition system on Raspberry Pi with a deep learning pipeline and Flask interface.
    Period
    Jun 2024 — Nov 2024
    Stack
    Raspberry Pi, Deep Learning, Flask
    • Built deep learning-enabled network slicing using RNNs for adaptive traffic management in next-generation networks.
    Period
    Jun 2024 — Nov 2024
    Stack
    Deep Learning, RNN
    • Designed an autonomous robot capable of navigating unpredictable surfaces to detect and reach fire sources.
    • Integrated sensor-driven fire detection with an automated water-pump extinguishing mechanism to suppress fires without human intervention.
    Period
    Nov 2023 — Oct 2024
    Stack
    Deep Learning, Raspberry Pi, OpenCV, Arduino, Sensors
    • Developed ML/DL predictive models using TensorFlow and scikit-learn on bioinformatics datasets, improving model accuracy through domain-specific feature engineering.
    Period
    Aug 2023 — Feb 2024
    Stack
    TensorFlow, Scikit-learn

About

I’m Tendool, an AI/ML and data engineer. The part I like best is what happens after the notebook — when a model has to answer a real question, run on real hardware, and be trusted by someone who will never read the code.

Since September 2025 I’ve been an AI intern at Yitro Global, working on small language models, graph-backed multi-agent systems and real-time voice agents for enterprise use. Alongside it I’m finishing a B.Tech in Artificial Intelligence & Data Science at ASE, Coimbatore.

Before that came university projects across quantum ML, healthcare data pipelines, robotics and agriculture. They taught me to care about the unglamorous parts: clean data, honest baselines, and testing against real inputs instead of mocks. I’m based in Bobbili, Andhra Pradesh, and work remotely.

What I work on

  1. 01

    Agentic AI & LLM systems

    Multi-agent and RAG architectures grounded in an organisation’s own documents, so answers come from policy rather than guesswork.

    HR query resolution, adaptive tutoring, multi-agent orchestration

  2. 02

    Computer vision & robotics

    Real-time detection on small hardware — a phone camera, a Raspberry Pi, a Jetson Nano — with speech in and out.

    SmartSight, Fire Fighting Robot, Robotic Hand

  3. 03

    Quantum machine learning

    Quantum neural networks and variational classifiers benchmarked honestly against classical baselines.

    Multimodal disease prediction

  4. 04

    Data engineering & big data

    Distributed HDFS pipelines that process prescription data at scale, and cleaning and analytics tools tested against the real data before any model is allowed near it.

    Prescription validation, BI agent over live board data

  5. 05

    Applied ML for energy & agriculture

    Predictive models for green-hydrogen electrolysis cells, and crop-disease identification from field photos.

    SOEC optimisation, AgriX

  6. 06

    Enterprise systems

    Graph-based clan clustering that surfaces candidate-to-role fits, and LLM chatbots that agentize CRM workflows end to end.

    Agentic CRM, talent-matching network, recruiter matching app

Toolkit

  • Daily driver
  • Proficient
  • Working knowledge

Languages & frameworks

  • Python
  • PyTorch
  • TensorFlow
  • CUDA
  • Keras
  • Scikit-learn
  • Matplotlib
  • C
  • Java
  • MATLAB
  • Spark
  • Scala

LLMs & agents

  • LLMs
  • Agentic AI
  • RAG
  • Multi-agent systems
  • Fine-tuning
  • Prompt engineering
  • Small language models
  • Text-to-speech
  • Speech recognition

ML & DL

  • Deep learning
  • Machine learning
  • NLP
  • Transformers
  • Generative AI
  • Data analytics
  • Optimisation
  • Reinforcement learning
  • Quantum ML

Data engineering & cloud

  • AWS
  • HDFS
  • Hadoop
  • DBMS
  • E2E Networks

Hardware & robotics

  • Jetson Nano
  • Raspberry Pi
  • Arduino
  • ROS

Engineering practice

  • Git & GitHub
  • CI/CD pipelines
  • Data structures & algorithms
  • OOP
  • DevOps

Education

  1. 2027

    ASE, Coimbatore

    B.Tech, Artificial Intelligence & Data Science

    CGPA 6.89 / 10In progress

  2. 2023

    Sri Viswa Junior College

    Class XII, MPC — Board of Intermediate Education, AP · Visakhapatnam

    93%

  3. 2021

    Swetha Chalapathi Samasthanam EM High School

    Class X — Board of Secondary Education, AP, Bobbili

    97.6%

Contact

Got something that has to work outside the notebook?

Elsewhere
GitHub LinkedIn
Phone
+91 93964 66665+91 94916 66665
Based in
Bobbili, VizianagaramAndhra Pradesh, India
Local time
ISTAvailable for roles now