Asrithavalli Penumalli
Generative AI Engineer • Orlando, FL, United States • a*********@gmail.com • +14******823 • linkedin.com/••••• • drivetube.ai/•••••
Professional Summary
Generative AI Engineer with 0 years of experience designing and deploying LLM-powered systems, RAG pipelines, and production ML services. Trained models achieving 89% F1 for production classification, built agentic workflows reducing manual effort by 65%, and deployed FastAPI inference on AWS using Docker and Kubernetes with CI/CD.
Technical Skills
Programming Languages: Python,Java,TypeScript,JavaScript,C++
Web Technologies: REST APIs
Frameworks and Libraries: PyTorch,TensorFlow,scikit-learn,Pandas,NumPy,LangChain,FastAPI,Flask,Node.js,Express.js,Spring Boot
Databases: SQL,PostgreSQL,MySQL,MongoDB,Redis,Vector databases,Indexing and query optimization
Cloud and DevOps: AWS,EC2,S3,ECS,Lambda,CloudWatch,Docker,Kubernetes,Terraform,GitHub Actions,CI,CD
Data and Analytics: XGBoost,MLflow,SciPy,Jupyter Notebooks
Tools and Methodologies: Git
Skills: HTML5,CSS3
LLMs & Retrieval: Hugging Face Transformers,FAISS,OpenAI API,Anthropic Claude,Embeddings,RAG pipelines,Prompt engineering,Agentic workflows
Backend & APIs: Microservices,Distributed systems
Work Experience
Narwal
Cincinnati, OH
Software Developer Intern, AI/ML
May 2025 – Oct 2025
Worked on AI/ML systems and LLM-powered RAG pipelines supporting a global manufacturing client; delivered model training, retrieval, and inference services.
Tech Stack: Python, PyTorch, LangChain, FAISS, FastAPI, PostgreSQL, MLflow, Docker, Kubernetes, GitHub Actions, Terraform, AWS
- Benchmarked DistilBERT against three model architectures using scikit-learn evaluation frameworks and MLflow tracking; production model reached 89% F1 on classification tasks.
- Designed and implemented LLM-powered agentic workflows with RAG retrieval and prompt engineering, reducing manual data lookup and decision workflows by 65% for a global manufacturing client.
- Built NLP preprocessing and tokenization pipelines for ~60K records using Python and PyTorch; standardized feature extraction and experiment metadata in MLflow for reproducible training.
- Implemented automated model retraining with drift detection and deployment triggers, shortening model update cycles and maintaining inference accuracy in production.
- Optimized PostgreSQL queries and created indexing strategies that reduced p95 API latency from ~450 ms to ~270 ms; deployed inference endpoints as FastAPI services on AWS.
- Containerized services with Docker, deployed on Kubernetes, and implemented CI/CD via GitHub Actions and Terraform; expanded automated test coverage from 55% to 75%, cutting release cycles from ~25 min to ~5 min.
University of Central Florida
Orlando, FL
Graduate Teaching Assistant
Aug 2025 – May 2026
Supported undergraduate and graduate courses in Python, machine learning, algorithms, and statistics; partnered with faculty on AI and data science curriculum.
Tech Stack: Python, Jupyter Notebooks, Pandas, scikit-learn, PyTorch
- Coached 100+ students on Python, machine learning concepts, statistics, algorithms, and system design through lectures, labs, and one-on-one support.
- Graded and provided detailed feedback on 250+ programming and ML assignments, ensuring timely turnaround and consistent evaluation using standardized rubrics.
- Collaborated with research faculty to refine AI and data science course materials, lab exercises, and assignment specifications to align with current industry practices.
Marlabs
Bengaluru, India
Full Stack Developer, AI/ML
Jan 2023 – Feb 2024
Delivered full-stack applications and ML-powered recommendations for enterprise clients; combined backend services with LLM/embedding-based retrieval.
Tech Stack: Python, PyTorch, LangChain, scikit-learn, Hugging Face Transformers, Spring Boot, React, PostgreSQL, AWS, MLflow
- Built ML-powered recommendation systems using pre-trained Hugging Face embeddings and XGBoost for three enterprise clients; evaluated models with cross-validation and standardized MLflow tracking.
- Designed and deployed LLM-based recommendation agents with RAG and semantic search to enable contextual retrieval, reducing data lookup time by 25% across two enterprise deployments.
- Standardized ML experiment tracking and model packaging across projects using MLflow, enabling reproducible training and streamlined deployment pipelines.
- Developed and shipped four production full-stack applications using Spring Boot and React; integrated backend ML services and maintained feature parity across environments.
- Monitored and resolved production incidents using AWS CloudWatch and log analysis, contributing to ~99.5% uptime across thousands of daily users.
- Implemented data indexing and query optimization in PostgreSQL and MongoDB to improve retrieval performance for recommendation and search features.
Projects
Epileptic Seizure Detection (Deep Learning)
Tools Used: Python, PyTorch, scikit-learn, NumPy, Pandas, Matplotlib
- Trained deep learning models on EEG time-series data for seizure classification using signal preprocessing and feature engineering across multiple architectures.
- Implemented end-to-end ML pipeline from raw signal processing through model training, evaluation, and visualization; results published in IEEE (2024).
Multi-Agent Research System
Tools Used: Python, LangChain, OpenAI API, FAISS, PyTorch, FastAPI, PostgreSQL, MLflow
- Architected a multi-step agentic workflow combining LLM query decomposition, RAG retrieval with FAISS, and fact verification to improve end-to-end response quality.
- Deployed FastAPI inference API on AWS with PostgreSQL conversation history, MLflow tracking, and CI/CD via GitHub Actions; observed measurable reductions in hallucination and improved accuracy.
Education
University of Central Florida
Master of Science in Computer Science • Orlando, FL • Aug 2024 – May 2026
Hindustan Institute of Technology and Science
Bachelor of Science in Computer Science — Gold Medalist • Chennai, India • May 2020 – May 2024
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.