Akhila Korrapati
Professional Summary
AI Engineer with 5+ years of experience designing and shipping production LLM and agentic AI systems in Python across AWS and Azure environments, including in a regulated financial services context. Specializes in multi-agent orchestration using LangGraph and LangChain on Amazon Bedrock, RAG and semantic retrieval over vector and graph stores, and scalable AI service delivery through FastAPI and Flask backends. Has delivered end-to-end MLOps pipelines on AWS SageMaker and Azure ML, deep learning models for anomaly detection and fraud analytics, and Kafka-driven asynchronous workflows. Proven ability to translate business requirements into measurable outcomes, including a 30% operational efficiency gain and a 50% reduction in model deployment cycle time. Brings expertise across the full AI engineering lifecycle — from fine-tuning Hugging Face transformers and knowledge graph retrieval to CI/CD, containerization, and production monitoring.
Technical Skills
Work Experience
- Architected multi-agent workflow automation using LangGraph and LangChain on Amazon Bedrock, enabling agents to reason over context, invoke external tools, and complete multi-step enterprise tasks autonomously.
- Built RAG pipelines using OpenAI embeddings and FAISS for semantic search and grounded document Q&A, extending retrieval accuracy by integrating Neo4j graph traversal for relationship-aware knowledge lookup.
- Integrated Pinecone and LlamaIndex into document retrieval services, managing indexing, chunking strategy, and query routing to support high-throughput knowledge base queries across enterprise content.
- Fine-tuned Hugging Face transformer models on domain-specific corpora to improve classification and generation accuracy within the multi-agent orchestration layer.
- Shipped AI services as asynchronous FastAPI and Flask REST APIs with MLflow model pipelines and PyTest-driven CI/CD, achieving a 30% improvement in operational efficiency through automated agent-driven workflows.
- Developed Go and Python backend microservices with Kafka event streaming and gRPC inter-service communication, enabling non-blocking, event-driven orchestration of AI pipeline stages.
- Containerized AI services with Docker and managed multi-service deployments on Kubernetes, integrating production monitoring and rollback hooks into the CI/CD pipeline.
- Designed MLOps pipelines on AWS SageMaker and Azure ML with automated model versioning and production monitoring, reducing model deployment cycle time by 50%.
- Built TensorFlow deep learning models for financial anomaly detection, training on transaction-level time-series data to surface high-risk patterns for the fraud analytics team.
- Developed PyTorch models for document classification and information extraction pipelines, supporting regulatory compliance workflows and structured data extraction from unstructured financial reports.
- Engineered LangChain and OpenAI-powered GenAI tooling for internal knowledge management, automating NLP-based document classification and reducing manual review overhead across operations teams.
- Optimized large-scale PySpark pipelines on Databricks processing millions of financial records daily, accelerating feature engineering throughput for model training and batch scoring jobs.
- Instrumented production model performance monitoring with statistical testing frameworks to detect data drift, trigger retraining, and maintain model reliability within compliance-sensitive financial workflows.
- Developed Scikit-learn classification and regression models for customer segmentation and revenue forecasting, delivering predictive insights to client marketing and operations teams.
- Designed and executed A/B and hypothesis testing frameworks to evaluate campaign variants, improving campaign effectiveness by 18% across targeted customer cohorts.
- Optimized ETL pipelines in collaboration with data engineers using Python and SQL, reducing data processing latency and ensuring consistent feature availability for model training.
- Built Power BI dashboards to automate recurring business intelligence reports, cutting report generation time and enabling self-service analytics for client stakeholders.
- Automated exploratory data analysis and model validation workflows with Python scripts, standardizing the team's preprocessing and evaluation process across multiple client engagements.
- Diagnosed data quality issues in upstream ETL sources using SQL profiling queries, reducing downstream model errors caused by missing and inconsistent feature values.
Projects
- Built a tool-using multi-agent assistant with LangGraph orchestration and RAG over FAISS for context-grounded enterprise workflow automation.
- Deployed the assistant as a FastAPI service containerized with Docker and orchestrated on Kubernetes with an integrated CI/CD pipeline.
- Built a tool-calling shopping agent with shop-by-image product search, enabling vision-based product discovery through external tool integrations.
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 140,000+ 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 - 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.