Skip to content

Charan Yelimela

AI Engineer Intern • Hyderabad, India • c*************@gmail.com • +91*******487 • linkedin.com/••••• • charanyelimela.vercel.app/•••••

Professional Summary

AI Engineer Intern with 0 years of experience designing, building, and deploying agentic AI and RAG systems for document intelligence, voice assistants, and education platforms. Skilled in Python development, LangChain and LlamaIndex retrieval stacks, OpenAI and LLaMA APIs, and vector database indexing (FAISS, Pinecone, ChromaDB) to deliver reliable retrieval and generation pipelines. Experienced in prompt engineering, prompt chaining, memory management, and tool/function calling to reduce hallucinations and automate multi-step workflows using n8n and REST APIs. Delivered production-style deployments and performance tuning (sub-second voice-agent latency) and built an LLM-powered ATS optimizer that shipped consistent high ATS scores. Familiar with Flask backends, Scikit-learn model pipelines, MySQL storage, containerization, and CI-oriented development practices. Seeking an internship to contribute to agentic AI product development and production RAG workflows.

Technical Skills

Programming Language: Python,SQL
Backend Technologies: Flask
Databases: MySQL
Cloud Platforms: Google Cloud Platform
Version Control & Development Tools: GitHub
DevOps & Infrastructure: Docker
API & Integrations: RESTful APIs,n8n
Data Analysis & Visualization: NumPy,Pandas
AI/ML Frameworks & Libraries: scikit-learn
Generative AI & LLMs: LangChain,LlamaIndex,OpenAI API,Llama,Groq,Whisper,Prompt Engineering
Vector Databases & RAG: FAISS,Pinecone,ChromaDB,Semantic Search
Architecture & Design Patterns: Orchestration

Work Experience

Frontlines EduTech (FLM)
Hyderabad
AI Research Intern
May 2025 – May 2026
Internship at an enterprise education-technology company focused on AI-powered automation and document intelligence for learning and HR workflows.
Tech Stack: Python, n8n, REST APIs, Prompt Engineering
  • Designed and implemented agentic automation pipelines using Python and n8n to orchestrate multi-step tool integrations, achieving a 70% improvement in workflow efficiency.
  • Built an LLM-powered ATS Resume Optimizer using prompt chaining and semantic matching to generate recruiter-aligned resumes, resulting in 90+ ATS evaluation scores in production.
  • Optimized prompt chains and retrieval settings to reduce hallucination rates in RAG flows using prompt engineering and embedding tuning without increasing inference latency.
  • Implemented robust REST API integrations and error-handling routines in Python for external tool calls, improving pipeline fault tolerance and retry behavior.
  • Documented agent configurations, prompt versions, and workflow architectures to standardize AgentOps handovers and reproducibility across student and product projects.
  • Implemented unit and integration checks for agent components and maintained reproducible environment specifications to accelerate onboarding and iteration.
Frontlines EduTech (FLM)
Hyderabad
AI Research Associate
June 2026 – Present
Research and evaluation role supporting AI product development, student project assessment, and production-readiness for agentic and retrieval systems at an edtech firm.
Tech Stack: Python, OpenAI API, LLaMA, FAISS, Pinecone
  • Led code and architecture reviews of student and prototype agentic systems, advising on memory management, tool/function calling, and guardrails to improve safety and reliability.
  • Evaluated RAG and retrieval pipelines for production readiness by assessing chunking strategies, embedding quality, and index configuration using FAISS and Pinecone concepts.
  • Delivered Python-based automation and utility libraries to the product codebase to standardize ingestion, embedding generation, and prompt templates across projects.
  • Partnered with product engineers to integrate LLM APIs and define API usage patterns that reduce cost and improve throughput for high-concurrency tasks.
  • Conducted controlled experiments to compare LLaMA and OpenAI API responses for curriculum and assessment tasks, documenting prompt variants and tuning guidance.
  • Prepared reproducible evaluation reports and technical recommendations for deploying agent components in staged environments and monitoring failure modes.

Projects

Agentic RAG System
Tools Used: Python, LangChain, LlamaIndex, FAISS, Pinecone, ChromaDB, OpenAI API, Docker, GCP, GitHub
  • Designed and implemented a modular RAG pipeline using LangChain and LlamaIndex to ingest, chunk, and index documents for retrieval-driven generation with OpenAI API.
  • Implemented embedding generation and multi-index management using FAISS and Pinecone to support semantic and hybrid search across large document sets.
  • Built retrieval and agent orchestration components in Python with strict prompt chaining to enable multi-step reasoning and tool/function calling.
  • Containerized components with Docker, managed source via GitHub, and deployed a test instance to GCP for integration testing and performance tuning.
Voice AI Support Assistant
Tools Used: Groq Whisper, LLaMA, Python, pyttsx3
  • Built and deployed a voice-based autonomous assistant that pipelines STT (Groq Whisper) into an LLM reasoning layer for multi-turn dialog.
  • Implemented prompt chaining and turn-state memory to maintain context across conversations using LLaMA-based inference.
  • Engineered TTS responses with pyttsx3 and optimized the inference pipeline to achieve sub-second end-to-end latency in a production-style environment.
  • Instrumented error handling and fallback prompts to gracefully recover from API failures and OCR/ASR errors.
ATS Resume Aid Buddy
Tools Used: Python, Flask, OpenAI API, Prompt Engineering, Semantic Search
  • Built a Flask REST API backend that orchestrates an LLM-based resume generation pipeline with semantic matching and iterative prompt optimization.
  • Implemented prompt chaining and refinement loops to align generated resumes to job descriptions and improve ATS compatibility.
  • Integrated document parsing and vector-based semantic search to select relevant candidate evidence for inclusion in generated resumes.
  • Documented the architecture and prompt chain designs to enable reproducible tuning and handover to engineering teams.
Medical Diagnosis Platform
Tools Used: Scikit-learn, Flask, MySQL, NumPy, Pandas, Python
  • Developed a full-stack ML diagnostic application with Scikit-learn models and Flask APIs to serve predictions to a web front end.
  • Engineered preprocessing and feature pipelines using NumPy and Pandas to improve model reliability and reduce noise in clinical inputs.
  • Trained and evaluated models using cross-validation and standard metrics, delivering ~90% diagnostic accuracy on the validation set.
  • Integrated persistent storage with MySQL and designed API endpoints for secure data ingestion and model inference.

Education

Institute of Aeronautical Engineering
B.Tech – Computer Science & Information Technology • Hyderabad • Nov 2022 – May 2026

Certifications

AI Mastery (GenAI / Agentic AI / RAG Systems) — Frontlines EduTech
Python Essentials 1 — Cisco Networking Academy
SQL Complete Bootcamp — Udemy
Walmart Software Engineering Job Simulation — Forage

Achievements

  • 3rd Prize — College Ideathon — 2024: Built an end-to-end IoT and data platform from abstract business requirements demonstrating data collection, processing, and analytics.

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

Explore Drivetube

  • Drivetube Profile — 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.
  • Free Job Board — verified openings crawled ATS-by-ATS from 100,000+ real company career pages across 35 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.
  • Job Hunt Program — managed job hunting, a one-time purchase from $199.99. JobScout matches verified roles to your real experience band, Blend AI writes a uniquely tailored resume and cover letter for every application, and the Autofill extension fills the form — or Let Us Apply submits it for you. Documentation.
  • Resume Writing Services — 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.
  • Community Membership — from $4.99/month (₹1,999/year in India). Unlocks the gated job-board filters — visa sponsorship, security clearance, workplace and application time — plus Job-Scout AI matching, Resume Report AI, Interview AI prep sheets, Recruiter Outreach AI sent from your own Gmail, Apply or Skip triage, a daily market feed and a $10,000+ library including 23 ATS-validated resume templates. Documentation.
  • Drivetube Hire — for employers — 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.

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

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