AI · LLMs · Agents · Research

Praneeth Vadlapati

Gen AI Developer & AI Engineer

~$ building production-ready AI systems

Professional profile

Production AI engineering, from research to deployment

Generative AI Developer, Full-stack AI Engineer, and Python Developer with 3 years of software engineering experience across agentic AI, LLM systems, AI evaluation, and production software.

Full résumé
Experience

AI & software engineering

AI Expert Snorkel AI · USA

Evaluating agentic systems to improve AI-agent reliability and performance; working across LLMs, Transformers, machine learning, and Python. Fine-tuned an LLM using SFT, LoRA, and DPO.

Software Development Engineer I · Associate SDE ZEE Entertainment Enterprises Limited

Built and deployed a production Python AI system for subtitle generation, led code-quality improvements, and reduced latency, memory usage, and hosting cost by 50%. The system supported 500 employees whose work reaches millions of users.

Education

AI & machine learning

University of Arizona Master of Science in Information Science — Machine Learning GPA 4.0 / 4.0 · Distinguished Graduate Scholar
Massachusetts Institute of Technology (MIT) Artificial Intelligence and Data Science program
Research & review

Academic and open-source work

Published academic research and contributed to open-source AI codebases spanning LLMs, agents, monitoring, telemetry, observability, prompts, and MCP.

Reviewed and judged AI papers for the ACL Industry Track, ALVR, and Springer conferences.

Technical capabilities

Skills & engineering stack

Core technologies and practices from the résumé, grouped by how they are applied across AI systems, software engineering, deployment, and evaluation.

Generative AI

PythonLarge Language ModelsTransformers LangChainLangGraphLlamaIndex OpenAI APIGemini APIHugging Face RAGEmbeddingsVector Search PineconeChromaDBPrompt Engineering Context EngineeringReasoningGraph Databases

Agentic AI

AI AgentsAgentic FrameworksCrewAI Model Context ProtocolMulti-Agent Systems Agentic ArchitecturesAgent-to-Agent Protocol Tool IntegrationMCP Clients & Servers

AI Engineering & Evaluation

DeepEvalAzure Evaluation SDKRagas Responsible AIAI SafetyGuardrails AI LLM MonitoringGenAI ObservabilityMLflow LangfuseWeights & BiasesOpenTelemetry Model LifecycleSFTLoRAUnsloth

AI Deployment & Cloud

Microsoft Azure AIAWS BedrockAWS SageMaker LLMOpsMLOpsModel Selection AI GovernanceCompliance StandardsAWS S3 Google Cloud Storage

Data Science & ML

Deep LearningNeural NetworksPyTorch NLPPandasNumPy MatplotlibSeabornData Wrangling Data VisualizationData Pipelines Structured DataUnstructured Data

Full-stack & DevOps

FastAPIFlaskREST APIs ReactNode.jsJavaScript GradioStreamlitChainlit SQLNoSQLMongoDBRedis KafkaGitLinux CI/CDDockerKubernetesTerraform
Featured AI projects Agent safety, RAG, reasoning routers, LLM tooling & open-source contributions LinkedIn in/prane-eth GitHub @prane-eth YouTube @PraneethVad
  • Gen AI
  • LLMs
  • AI Agents
  • RAG
  • Python
  • LangChain
  • LangGraph
  • MCP
  • Prompt Engineering
  • LLM Monitoring
  • Evaluation
  • Fine-tuning
  • PyTorch
  • Azure
  • Deployment
  • Observability