Skip to content

Ajith Adhithya MukkerA

Junior AI Engineer • Hyderabad, India • drivetube.ai/•••••

Professional Summary

Junior AI Engineer with 0 years of experience building Generative AI and NLP applications focused on LLM-based systems and retrieval-driven assistants. Skilled in designing Retrieval-Augmented Generation (RAG) pipelines, embeddings-based evidence matching, and prompt/structured tool-calling workflows using Python and Sentence Transformers. Experienced integrating LLM runtimes (Gemini, OpenAI, Ollama) with production backends via FastAPI and WebSockets and operationalizing vector search using Qdrant. Delivered features for career platforms and conversational coaching systems, including a resume-evidence matching engine and an adaptive mock-interview pipeline, and contributed to multi-model evaluation sprints. Comfortable owning end-to-end ingestion, retrieval, and evaluation workflows, improving retrieval relevance and reducing hallucination risk through context engineering and targeted prompt interventions.

Technical Skills

Programming Language: Python,JavaScript,Text Preprocessing
Backend Technologies: FastAPI,REST APIs
Databases: PostgreSQL
Version Control & Development Tools: GitHub,Docker
Data Analysis & Visualization: Model Training,Streamlit
Machine Learning & AI: Classification,Structured Tool Calling,Feature Engineering,scikit-learn
Generative AI & LLMs: TF-IDF,Embeddings,OpenAI,Gemini,Ollama
Vector Databases & RAG: Qdrant,Sentence Transformers,RAG

Work Experience

Social Tek AI & Business Solutions
Hyderabad, India
Junior AI Engineer
Feb 2025 – Present
Built generative-AI features and conversational systems for Ziro.digital (career platform) and related AI coaching products, focusing on retrieval, evaluation, and production integrations.
Tech Stack: Gemini 3 Flash Preview, Gemini Live, OpenAI, Sentence Transformers, JavaScript
  • Architected the AI Resume feature for Ziro.digital using Gemini 3 Flash Preview and structured tool calling to generate JD-targeted, ATS-friendly resumes with unsupported-claim detection.
  • Designed an evidence-matching layer with Sentence Transformers embeddings to align student skills and projects to job descriptions and prevent hallucinated credentials.
  • Developed the adaptive mock-interview engine, implementing question-adaptation logic and a transcript analysis pipeline that scored responses and produced targeted practice roadmaps.
  • Implemented a persistent WebSocket stream to Gemini Live to enable low-latency native-audio conversations between browser clients and the model.
  • Drove model-evaluation sprints performing error analysis, retrieval testing, and prompt evaluation; documented failure modes and recommended retrieval and prompt adjustments to improve response relevance.
  • Delivered multi-model AI systems combining Gemini and OpenAI models for Ziro.digital, part of a platform used by 68.8K+ visitors over a 90-day period.
  • Developed a browser-side audio capture demo using JavaScript to stream microphone data to the WebSocket session for low-latency voice interactions.
Social Tek AI & Business Solutions
Hyderabad, India
Data Science Intern
Aug 2024 – Jan 2025
Supported chatbot and NLP initiatives including dataset preparation, baseline modeling, and evaluation to improve intent detection and conversational quality.
Tech Stack: Python, TF-IDF, scikit-learn, PostgreSQL, REST APIs, GitHub
  • Processed and labeled conversational datasets and implemented text preprocessing pipelines in Python to produce training-ready data for intent models.
  • Implemented TF-IDF and sentence-transformer baselines for intent classification and evaluated model performance using scikit-learn metrics to guide model selection.
  • Developed data pipelines for chat logs, cleaned and tokenized messages, and stored processed features in PostgreSQL to support model training workflows.
  • Validated model outputs with test harnesses, documented failure cases, and produced recommendations to improve context handling and prompt design.
  • Supported integrating chatbot backends with REST APIs and supported WebSocket session handling for live demonstrations.
  • Authored evaluation reports and maintained preprocessing notebooks and model artifacts in GitHub to enable reproducible experiments.

Projects

Workspace Memory AI | 2026 – 2026
Tools Used: Python, FastAPI, Qdrant, Sentence Transformers, RAG, Docker, Ollama, Streamlit
  • Engineered an end-to-end document ingestion pipeline with semantic chunking and custom embedding generation using Python and Sentence Transformers.
  • Implemented metadata-aware vector search in Qdrant with context-expansion heuristics to improve retrieval relevance for semantic Q&A.
  • Designed an intent-based RAG routing layer to dispatch queries between a local LLM running on Ollama and the vector store, served via FastAPI.
  • Containerized the application with Docker and built a Streamlit demo interface for a local-first AI workspace memory assistant.

Education

Chaitanya Deemed to be University
Bachelor of Technology (B.Tech) – Mechanical Engineering • 2023

Powered by Drivetube · Create your own profile at drivetube.ai

Everything on Drivetube

Six products, two of them free forever. Start wherever you are.

Read the docs →
  • Your free digital resume

    at drivetube.ai/in/your-name: one true standard resume with a Hiring Snapshot (visa status, expected salary, notice period, work preference, relocation), an ATS-ready PDF download and a single shareable link. Free forever; interview requests come from verified employers and your contact details stay masked until you accept.

    Documentation
  • Verified jobs, posted in the last 3 days

    verified openings crawled ATS-by-ATS from 160,000+ real company career pages across 50+ ATS platforms. Shows the true posting date from the source ATS — not when a listing was indexed — and deletes every general listing 3 days after it was actually posted. No ghost jobs, no ad-sponsored listings, no staffing reposts, no account needed.

    Documentation
  • Written by senior career writers

    human-written, ATS-optimised resumes by senior career writers, from ₹499.99 / $25.99. Available in every country, written to the destination country's own standard — a US resume, UK CV, German Lebenslauf and Indian resume are genuinely different documents. A paid service, separate from the free Drivetube Profile.

    Documentation
  • Drivetube OneFrom $39.99 / 3 mo

    Daily matched jobs, tailored resumes, or we apply for you

    Drivetube's paid service. Community sends daily Jobsheets of fresh jobs matched to your profile on WhatsApp and email, with the Drivetube Community ($39.99 for 3 months or $69.99 for 6 months; ₹999 or ₹1,899 in India). Jobhunt is one-time application credits with Community included: one credit tailors one resume and its cover letter (100 for $99 with 3 months of Community, 250 for $199 with 6 months). Let Us Apply is an add-on to Jobhunt: a human expert applies 250 times for you on your credits ($0.60 each, $150). Everything lives on one dashboard at drivetube.ai/drivetubeone.

    Documentation
  • For employers — no job postings, no applications

    hiring with no job postings and no applications. Paste your real job description and AI matches it against candidates' true standard resumes, returning ranked candidates with a match %, matched and missing skills and written reasoning. Free tier included; employers pay, candidates never do.

    Documentation
  • Documentation

    every product explained in full, with feature-by-feature comparisons against the job boards, AI apply tools, resume services and hiring platforms people actually use.

  • Playbooks

    tactical job-search guides. Each post is one named tactic with the situation it applies to, the exact steps, a copy-paste message and honest failure modes. Free, no account.

The job board covers the United States, India, United Kingdom, Canada, Europe and Australia, and Resume Writing Services are available in every country.

Pricing is identical on the web, iOS and Android — no app-store markup. Monthly Community membership is purchased in the iOS app only; the website sells annual plans. The Android app has no in-app purchase, so Android members subscribe on drivetube.ai and then sign in to the app with full access. Membership follows your account, not your device.