Pavan Kumar Gorla
Professional Summary
AI Software Engineer with 5 years of experience building production-grade LLM systems, agentic AI, and scalable ML pipelines for FinTech and enterprise platforms. Strong hands-on experience with Python-based model development, LangChain/GPT-driven agents, and Transformer fine-tuning using Hugging Face. Delivered high-throughput data processing (Spark, Databricks, Snowflake) and orchestrated ETL with Airflow and Delta Lake to support feature engineering at scale. Owned MLOps and deployment stacks using Docker, Kubernetes, MLflow, Jenkins, and AWS SageMaker to shorten release cycles and improve model reliability. Proven track record deploying real-time fraud detection and conversational agents that operate at hundreds of thousands to millions of interactions monthly. Comfortable taking end-to-end ownership from research and prompt engineering to production monitoring and cost optimization.
Technical Skills
Work Experience
- Architected LLM-based conversational agents using LangChain and GPT to serve 250K+ monthly queries and automate common customer intents.
- Built agentic workflows that integrated external APIs and tool hooks via LangChain to enable autonomous decision-making for support automation.
- Designed real-time fraud scoring pipelines that combined Kafka streaming signals with contextual LLM embeddings to surface risky transactions.
- Implemented inference-serving infrastructure with Docker and Kubernetes to scale model workloads and stabilize inference across deployments.
- Deployed CI/CD and monitoring automation with Jenkins and AWS to enable safe model rollouts and rapid rollback when anomalies were detected.
- Optimized prompt templates and batching strategies to reduce compute per request and lower model cost while preserving accuracy.
- Engineered an NLP automation pipeline using Hugging Face Transformers and spaCy to process 10M+ documents monthly for payments reconciliation.
- Developed fraud detection models in Python that leveraged Transformer embeddings for downstream classification, improving detection accuracy by 26%.
- Built end-to-end ML pipelines on Databricks and Apache Spark and optimized Spark SQL for robust feature extraction and training throughput.
- Implemented CI/CD for model packaging and deployment with MLflow and Docker to reduce deployment errors and accelerate releases.
- Integrated model monitoring and alerting feeding Snowflake-based analytics to detect drift and trigger retraining workflows.
- Translated model outputs into production decision pipelines for payments and risk teams to automate actions and lower manual reviews.
- Designed multilingual NLP pipelines with spaCy and Hugging Face to process 15M+ documents monthly for financial compliance ingestion.
- Improved entity recognition models through fine-tuning and augmentation, increasing recognition accuracy by 27%.
- Automated training and experiment tracking with MLflow and Kubernetes, shortening production release cycles from 3 weeks to 5 days.
- Built computer vision models using TensorFlow and OpenCV to automate defect detection and reduce manual inspections.
- Engineered ETL and feature pipelines with Apache Airflow, Delta Lake, Apache Spark and Databricks to support fraud anomaly detection.
- Deployed AI microservices via Jenkins CI/CD and AWS SageMaker to productionize models and enable reproducible end-to-end solutions.
Projects
- Implemented an autonomous agent using LangChain and GPT that chained tool calls to complete multi-step tasks.
- Designed prompt templates and memory strategies to improve task consistency across agent runs.
- Integrated simple API tools into the agent to enable contextual actions and external data retrieval.
- Built a retrieval-augmented generation chatbot that combined dense vector search with Transformers for contextual responses.
- Engineered vector database integration and chunking strategies to improve retrieval relevance for domain documents.
- Evaluated relevance and response quality and iterated on embedding strategies to reduce hallucination.
- Created prompt engineering pipelines to standardize template generation, A/B compare outputs, and automate prompt tuning.
- Established metrics for output consistency and implemented automated evaluation to guide prompt refinements.
Education
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 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 ProgramFrom $199.99
We run your job hunt for you
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 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 - Community MembershipFrom $49.99/yr
AI tools, gated filters and a $10,000+ library
from $49.99/year (₹1,999/year in India), or $4.99/month in the iOS app. 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 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.