Senior AI Engineering

LLM & RAG Consulting for Real-World Products

Stop building demos. Start shipping production-grade AI applications. Specializing in OpenAI, Anthropic, Gemini, and complex RAG architectures that actually work.

Core Stack Expertise

OpenAI Anthropic Gemini LangChain / LlamaIndex Vector DBs

How I Can Help

Turning generative AI hype into reliable, scalable software infrastructure.

LLM App Architecture

  • Scalable backend design
  • Streaming & async handling
  • Low latency optimization

Advanced RAG

  • Hybrid search & reranking
  • Context window management
  • Citation & sourcing

Eval & Guardrails

  • Automated evaluation
  • Safety & PII filtering
  • Hallucination reduction

Model Strategy

  • Model selection (Open vs Closed)
  • Fine-tuning vs Prompting
  • Cost optimization analysis
Deep Expertise

End-to-End RAG Pipelines

I don't just use standard libraries. I build robust pipelines that handle complex data ingestion, smart chunking, hybrid retrieval strategies, and post-retrieval reranking.

My systems include feedback loops and monitoring to ensure answers remain accurate over time.

Ingest
Index
Rerank
Generate
// Continuous Evaluation Loops Included

Recent Work

Solving real business problems with LLMs, not just demos.

SaaS
Customer Support

Support Copilot

Fine-tuned LLM system to assist agents with draft responses and policy lookup.

+25% Improvement in CSAT

Reduced handle time by 30%

Enterprise
RAG

Internal Knowledge Search

RAG system over 50k+ internal documents with citation and source linking.

92% Retrieval Accuracy

Replaced legacy keyword search

FinTech
Compliance

Compliance Assistant

Chatbot with strict guardrails, PII masking, and full audit logging.

0% PII Leakage

Passed 3rd party security audit

About Morty Morty

I am a senior AI Engineer focused on the practical application of Large Language Models. Unlike many who just prompt engineering, I bring a systems thinking approach to AI.

I help companies move from "cool demo" to "reliable product" by addressing the hard problems: latency, cost, evaluation, and non-deterministic behavior. I have a proven track record of shipping AI features that users actually trust.

30+
Projects Shipped
4+
Years in AI

The Toolbox

Models & APIs

OpenAI GPT-4 Anthropic Claude 3 Google Gemini Mistral Hugging Face

Engineering

Structured Outputs (JSON) Function Calling / Tools Streaming Responses Embeddings

Infrastructure

Pinecone / Weaviate LangChain Eval Harnesses

"Morty helped us reduce our LLM costs by 40% while actually improving response quality. His knowledge of prompt engineering is next level."

— Sarah J., CTO at TechFlow

"The RAG pipeline Morty built for our internal docs is incredibly fast and accurate. Our support team uses it daily."

— Mike R., Product Lead

Let's Talk AI

Ready to build something real? I'm currently accepting new projects.

Booking Oct/Nov

Engagement Types

  • • Strategic Advisory
  • • MVP Build / Prototyping
  • • System Audit & Optimization