Vinay Aluguri | Generative AI Engineer | Agentic AI Engineer

01 //

System Overview

AI Engineer specializing in Generative AI, Agentic AI, and AI-powered full-stack application development. Experienced in building LLM-powered applications, RAG pipelines, multi-agent systems, and AI-driven automation workflows using Python, FastAPI, LangChain, and CrewAI.

Skilled in prompt engineering, API integrations, LLM evaluation, agent behavior testing, and troubleshooting AI workflows. Focused on transforming business requirements into practical AI solutions by developing end-to-end applications, integrating AI capabilities with existing systems, and bridging AI engineering and customer-facing solution delivery through a Forward Deployed Engineering approach.

Engine Designation Gen AI | Agentic AI | Forward Deployed

Primary Node Proddatur, Andhra Pradesh, India

Secure Pipeline vinayaluguru@gmail.com

Direct API Dial +91 9100129701

Professional Index LinkedIn Profile

02 //

Execution Pipeline

AI Engineer

Turing (Remote)

MAR 2025 – JUL 2026 · 1 YR 5 MOS

Developed RAG and multi-agent AI systems, contributing to architecture, implementation, workflow testing, and AWS deployment.
Built backend services and REST APIs to support AI-powered workflows and integrations.
Integrated commercial LLM APIs into AI-enabled application workflows.
Evaluated workflows for task completion, retrieval relevance, groundedness, latency, hallucination rate, and response quality.
Worked with LangChain, CrewAI, MCP, and n8n for agent orchestration, tool integration, and workflow automation.
Investigated runtime and workflow failures through debugging, testing, and failure analysis.
Used AI coding assistants to support development, debugging, testing, and code review.

LLM S2 Annotator (OpenClaw CUA Trajectory Specialist)

Turing (Remote)

NOV 2024 – JAN 2025 · 3 MOS

Created computer-use agent trajectories from natural-language instructions to assess multi-step agent behavior.
Evaluated model responses for reasoning quality, factual accuracy, safety, instruction adherence, and task completion.
Performed prompt evaluation, pairwise response ranking, and hallucination detection.
Analyzed interaction traces and validated tool calls to investigate execution failures.
Evaluated multi-turn reasoning, execution consistency, context retention, and adherence to evaluation criteria.
Contributed to evaluation guidelines and trajectory-alignment datasets.

LLM Agentic Trainer

Turing (Remote)

AUG 2024 – OCT 2024 · 3 MOS

Worked with Python, SQL, Git, JSON, and TAU in AI training and evaluation tasks.
Designed structured agent workflows, JSON task definitions, tool integrations, and benchmark prompts.
Applied zero-shot, few-shot, Chain-of-Thought, and ReAct prompting approaches.
Performed RLHF-oriented evaluation of reasoning, trajectory accuracy, and output quality.
Documented evaluation guidelines and analyzed agent failures to improve task instructions and evaluation criteria.

Python Full Stack Development Intern

Global Quest Technologies

AUG 2023 – JUL 2024 · 1 YR

Developed web applications and backend services using Python, FastAPI, REST APIs, SQL, HTML, and CSS.
Built and integrated RESTful APIs for application features and frontend-to-backend communication.
Worked with databases, debugging, testing, Git, and application development workflows.
Troubleshot application issues and supported feature development, integration, and testing.

03 //

Systems & Showcase

Agentic RAG // Workflow [ PRODUCTION RAG ]

Agentic RAG Research Assistant

Developed a two-agent workflow in which a router selects document retrieval, web search, or direct LLM response based on user questions. Integrated PDF text-splitting, FAISS vector embeddings, Groq LLM inference, and web search for verified answer synthesis.

Python CrewAI Groq FAISS Embeddings Web Search LangChain

Agentic AI // Orchestration [ DEPLOYED ON AWS ]

Multi-Agent AI Automation Platform

Developed a multi-agent workflow for research, planning, content generation, and task execution using CrewAI. Designed Researcher, Planner, Writer, and Reviewer agent roles with FastAPI REST API orchestration, testing task completion, reasoning consistency, and edge cases.

Python FastAPI CrewAI LangChain REST APIs Web Search AWS

Security & Guardrails [ EVALUATION SUITE ]

AI Agent Security & Guardrails Evaluation

Implemented input checks for prompt-injection and jailbreak phrases with allow/block decisions. Added automated PII redaction (email and phone numbers), unsafe output checks, and an automated pass/fail evaluation test suite analyzing false positives.

Python Regex Input Validation PII Redaction Output Checks Failure Analysis

Conversational Voice AI [ REALTIME ONBOARDING ]

Sarvam AI Voice Agent — Delivery Onboarding

Designed a voice-agent flow for delivery-partner lead qualification and onboarding. Integrated a verification-service API testing HTTP 200/500 scenarios with conversational guardrails for intent confirmation, ambiguity handling, and controlled termination.

Sarvam AI Genie Voice AI Prompt Engineering API Integration HTTP Testing

Workflow Automation [ N8N & GPT-5 MINI ]

Intelligent Invoice Processing Automation

Planned an n8n workflow for invoice intake and AI-assisted extraction of structured invoice data using OpenAI GPT-5 mini. Designed validation and routing rules for missing fields, duplicate invoices, human approval workflows, and deterministic rule execution.

n8n OpenAI GPT-5 mini OCR/PDF Extraction REST APIs Database Integration

04 //

Intelligence Matrix

Core LLM & Generative AI

Core LLM Stack & Python 96%

Python, LangChain, SQL, FastAPI REST APIs, Microservices architecture.

Generative AI & Vector DBs 94%

LLM Internals, Prompt Tuning, Embeddings, ChromaDB, FAISS, Pinecone.

Agent Workflows & RAG 95%

CrewAI, MCP Protocol, Semantic Search, Tool Calling, Hallucination Detection.

Frameworks & Cloud Infrastructure

AI Frameworks & Tooling 92%

LangChain, Hugging Face, CrewAI, MCP, n8n, Cursor, Claude Code, Copilot.

Cloud & DevOps (AWS & Docker) 91%

AWS EC2, Docker Containerization, Git, GitHub Actions CI/CD, REST API Microservices.

Evaluation & Engineering Practices 93%

Retrieval Accuracy, Latency Tracking, SxS Ranking, Technical Documentation.

Engineering
Agentic AI Systems

System Overview