AI Engineer

Production AI Systems That Actually Work

I build LLM applications, RAG systems, autonomous agents, and voice AI — engineered with guardrails, structured outputs, and deterministic state machines.

LLMsRAGAI AgentsVoice AI

Technical Skills

What I bring as a AI engineer

LLM & Foundation Models

Claude 3.7 / Sonnet— Reasoning & structured output
OpenAI GPT-4o— Embeddings & chat completions
LangChain— Retrieval chains & tool use
LangGraph— Multi-agent state machines

RAG & Vector Systems

pgvector— HNSW vector embeddings in PostgreSQL
Hybrid RAG— Dense + BM25 sparse reranking
Semantic Chunking— Document parsing with metadata
Cohere Reranking— Cross-encoder precision scoring

Voice AI & Audio

Whisper— Speech-to-text transcription
ElevenLabs— Natural voice synthesis
WhatsApp Voice— Audio note processing pipeline
Intent Extraction— Structured CRM output from audio

AI Infrastructure

FastAPI— Async LLM streaming backends
Redis— Semantic caching & rate limiting
Pydantic / Zod— Structured output validation
BullMQ— Background AI job queues

Architecture

How I architect ai systems

01

Data Ingestion

Parse documents (PDF, HTML, audio) into structured chunks with metadata preservation and semantic boundaries.

02

Embedding & Indexing

Generate dense vector embeddings via OpenAI/Cohere, store in pgvector with HNSW indexing for sub-100ms retrieval.

03

Hybrid Retrieval

Combine dense semantic search with BM25 keyword matching, apply reciprocal rank fusion and cross-encoder reranking.

04

LLM Reasoning

Route through Claude/GPT with deterministic prompt templates, structured JSON output, and citation enforcement.

05

Guardrails & Output

Validate via Pydantic/Zod schemas, apply hallucination prevention, and stream results with source attribution.

Featured Work

Production projects as a AI engineer

Gen AI & VoiceLive in Production

Kookabe AI Suite

Enterprise WhatsApp RAG Chatbot & Automated AI Voice Mail

Problem

Companies received hundreds of repetitive WhatsApp voice notes, PDFs, and product inquiries daily, resulting in 4-8 hour response delays and missed sales leads.

Solution

Built a hybrid RAG system with pgvector and Claude 3.7 that parses customer inquiries, searches internal PDF documentation, and generates accurate answers with human-handoff triggers.

Architecture

  • WhatsApp Business API webhooks ingesting incoming text, voice notes, and document files
  • Hybrid RAG combining pgvector dense embeddings with BM25 keyword reranking
  • FastAPI backend handling asynchronous LLM streaming and conversation state
  • Automated audio transcription pipeline extracting lead data directly into CRM webhooks

Verified Results

Automated over 90% of routine inquiries with sub-3-second first responsesZero hallucinations verified via strict citation and source-chunk verificationContinuous 24/7 uptime handling high-volume customer messages
LangChainClaude 3.7FastAPIPostgreSQL / pgvectorWhatsApp Cloud APIRedis
View Live

Experience

Where I've applied these skills

AI & Full-Stack Engineer

atUpworkTop Rated

May 2026 — Present

Delivering production AI workflows, full-stack Next.js/NestJS platforms, and cloud DevOps systems for high-growth tech startups and international clients.

  • Consulting on AI agent architecture, hybrid RAG pipelines, and conversational voice systems.
  • Building scalable REST APIs, microservices, and database schemas with PostgreSQL and Prisma.
  • Maintaining a 100% Job Success Score with verified 5-star client contracts.
AI AgentsLangChainClaude 3.7Next.jsNestJSPostgreSQLDocker

Process

How I work

01

Understand the Domain

Map your data sources, user queries, and accuracy requirements before writing a single line of code.

02

Architecture Design

Design the retrieval pipeline, model selection, embedding strategy, and guardrail layers.

03

Iterative Development

Build in sprints with measurable retrieval accuracy metrics, not just vibes.

04

Production Hardening

Add caching, rate limiting, fallback models, monitoring, and cost governance before shipping.

FAQ

Frequently asked questions

What makes your RAG systems different from basic implementations?

I build hybrid RAG with dense embeddings + BM25 sparse search, reciprocal rank fusion, and cross-encoder reranking. Every answer includes strict source citations and hallucination prevention guardrails — not just naive vector similarity.

Do you build multi-agent systems?

Yes. I use LangGraph for cyclical state machine architectures with persistent checkpointing, dead-loop prevention, and explicit human-in-the-loop approval gates for critical operations.

Can you integrate AI into an existing product?

Absolutely. I specialize in embedding AI capabilities into production SaaS — streaming completions, token-budgeted prompt caching, semantic caching with Redis, and graceful degradation when model providers experience latency.

What about voice AI and audio processing?

I build voice qualification pipelines — WhatsApp audio transcription via Whisper, intent extraction into structured CRM data, and natural voice synthesis responses with ElevenLabs.

Need a production AI system built?

From hybrid RAG to autonomous agents — I engineer AI that works in production, not just in demos.