Rakesh Geddam
Professional Summary
AI Engineer with 4+ years of experience specializing in Data Engineering, Generative AI, Machine Learning, and Cloud Data Platforms across banking, healthcare, enterprise AI, and research domains.
Technical Skills
Work Experience
- Engineered innsight-ai, an enterprise multi-agent platform using Google ADK (LlmAgent, SequentialAgent, ParallelAgent, AgentTool) deployed in Gemini Agent Platform with a Master Orchestrator delegating tasks across Marketing, Operations, and Customer Experience agent teams.
- Architected an 8-parent and 23-subagent AI orchestration framework using Google ADK that automated shipment exception investigations, reducing manual analysis effort by 80%.
- Engineered FastAPI microservices with JWT authentication and React TypeScript dashboards on GCP Cloud Run, delivering average response times below 2 seconds for enterprise pilot users.
- Developed a dual-schema PostgreSQL database with pgvector to support RAG-powered retrieval, improving AI response accuracy by 35% while maintaining complete audit traceability.
- Integrated parallel Gemini and Claude development workflows using Git worktrees and feature flags, reducing integration conflicts by 40% and accelerating multi-agent feature delivery.
- Delivered full-stack production services (FastAPI backend and React/TypeScript dashboards) on GCP Cloud Run backed by pgvector HNSW staged retrieval, Terraform IaC, GitHub Actions CI/CD pipelines, and 75 passing unit/integration tests plus Playwright e2e suites.
- Spearheaded the development of a SwiftUI-based iOS productivity application that acquired 5,000+ monthly active users within six months of App Store launch.
- Constructed Snowpipe Streaming and Python ELT pipelines to process 300K+ daily application events, maintaining data freshness with under 10-second ingestion latency.
- Configured Snowflake Cortex semantic models to enable natural language analytics, reducing business report turnaround time for product stakeholders.
- Optimized Antigravity agentic AI workflows with token-aware state management, decreasing LLM context window failures by 80% and improving response reliability.
- Delivered interactive Streamlit-in-Snowflake dashboards that surfaced real-time product metrics and AI-driven retention insights, accelerating feature validation.
- Orchestrated end-to-end CI/CD pipelines through Xcode Cloud with secure AWS S3 artifact management, enabling weekly automated releases with minimal operational overhead.
- Customized Gemini-powered conversational workflows for appointment scheduling, billing, and patient FAQs, automating routine support requests and reducing manual triage effort by 75% for 300+ patients each month.
- Automated patient intake workflows using Google Apps Script, streamlining data collection and form processing to reduce onboarding time from 30 minutes to under 5 minutes while improving operational efficiency.
- Enhanced React dashboards by resolving WCAG 2.1 accessibility issues, achieving a 100 Lighthouse Accessibility score and delivering a consistent user experience across desktop and mobile devices.
- Secured RESTful application endpoints with OAuth 2.0 and JWT authentication, strengthening role-based access control and supporting HIPAA-aligned security requirements for sensitive patient information.
- Validated application quality by developing Jest and React Testing Library test suites with component coverage, minimizing UI regressions and improving release stability across new feature deployments.
- Improved Gemini chatbot performance by curating conversational datasets and building evaluation pipelines, increasing intent recognition accuracy by 22% while delivering more reliable responses for patient interactions.
- Engineered TensorFlow LSTM models to predict graphene energy absorption from molecular simulation data, reducing simulation analysis time by 50% while improving model performance for research workflows.
- Evaluated LSTM, Support Vector Machine, and Linear Regression models, decreasing prediction error from an MSE of 576 to 52 across complex multi-dimensional scientific datasets.
- Standardized machine learning environments using Docker containers, ensuring reproducible model training and consistent execution across three distributed research computing clusters.
- Devised Python-based data validation scripts that identified and filtered 140+ corrupted simulation files before training, strengthening dataset integrity and pipeline reliability.
- Published machine learning research as a co-author in a peer-reviewed ASME paper, contributing predictive modeling insights for graphene energy absorption studies.
- Championed machine learning workflow adoption by presenting technical findings to a 15-member multidisciplinary research team, increasing utilization of data-driven simulation methodologies.
- Directed the migration of 100+ TB of consumer banking data from Teradata to Hive on AWS EMR, automating six PySpark validation workflows and reducing migration cycle time from one week to 48 hours.
- Refined distributed PySpark ETL pipelines through partitioning and caching strategies, improving large-scale data processing performance by 25% across enterprise Hadoop workloads.
- Crafted Oracle PL/SQL procedures to validate cross-platform data migration, maintaining data accuracy and ensuring consistent reconciliation between legacy and target systems.
- Streamlined reusable Python libraries for ETL orchestration, configuration management, and credential handling, reducing development effort by 35% across five engineering teams.
- Established database roles, schemas, and access controls using least-privilege principles, securing data access for 50+ analysts and engineers across production environments.
- Strengthened production data pipeline reliability by implementing monitoring and automated alerting for lock contention and memory exceptions, sustaining pipeline availability.
Education
Certifications
Powered by Drivetube · Create your own profile at drivetube.ai
Everything on Drivetube
Six products, two of them free forever. Start wherever you are.
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 BoardFree
Verified jobs, posted in the last 3 days
verified openings crawled ATS-by-ATS from 115,000+ real company career pages across 54 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 - Resume Writing ServicesFrom $25.99
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 - Drivetube HireFree tier
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.