Pargev Khachatryan
@pargevkhachatryan
AI developer building production LLM systems—agents, RAG, and backend architecture from idea to MVP.
What I'm looking for
I’m an AI developer with 6 years of software engineering experience, the last 4 focused on LLM-powered systems in production. I design backend architecture for AI components and integrate both commercial and open-source LLMs, then ship reliable capabilities end-to-end with product teams.
At NetFactory, I’ve owned the backend architecture for AI components, building a FastAPI microservice layer serving LLM agents to 120+ partner restaurants. I built a conversational AI agent (LangChain + LangGraph) for table booking and food ordering in natural language, and designed a RAG system over menus, reviews, and restaurant policies (Qdrant, hybrid semantic + keyword retrieval) that answers guest questions with 94% accuracy on an internal evaluation set.
I also improved model economics and quality by integrating and A/B-testing GPT-4o, Claude, and Llama 3.1, including fine-tuning Llama 3.1 8B on 40k dialogue transcripts, cutting inference cost by 63%. Earlier at Aratech Solutions and Codewave LLC, I developed document intelligence for fintech (parsing, embedding, semantic search over 2M+ contracts and invoices) and shipped REST APIs and CI/CD for a logistics SaaS—reducing Transformer inference latency 4× via ONNX export, quantization, and batching.
Experience
Work history, roles, and key accomplishments
AI Developer
NetFactory
Jan 2026 - Present (7 months)
Owned the backend architecture for AI components, including a FastAPI microservice layer serving LLM-powered agents for table reservations and food ordering. Built a LangChain/LangGraph conversational agent and a Qdrant-based RAG system, integrated and fine-tuned commercial/open-source LLMs, and implemented an automated LLM evaluation harness for release gating.
Machine Learning Engineer
Aratech Solutions
Jun 2021 - Feb 2023 (1 year 8 months)
Developed a document-intelligence service for a fintech client, performing parsing, embedding, and semantic search over 2M+ contracts and invoices. Shipped a GPT-3-based internal knowledge assistant to production and improved Transformer inference latency using ONNX export, quantization, and batching.
Education
Degrees, certifications, and relevant coursework
Yerevan State University
Bachelor of Science, Informatics and Applied Mathematics
2014 - 2018
Completed a BSc in Informatics and Applied Mathematics at Yerevan State University.
Tech stack
Software and tools used professionally
Availability
Location
Authorized to work in
Job categories
Interested in hiring Pargev?
You can contact Pargev and 90k+ other talented remote workers on Himalayas.
Message PargevGet matched with your dream remote job
Sign up now and join over 250,000+ remote workers who receive personalized job alerts, curated job matches, and more for free!
