Haystack
← Back to Jobs
Technology

AI Engineer (GenAI / Agentic AI / LLM Engineer

Lorven Technologies, Inc.Dallas, TX🇺🇸United StatesPosted 21 Jul 2026

Why This Role Stands Out

Leverage your expertise in GenAI, LLMs, and RAG to build cutting-edge agentic AI applications in a hybrid environment with significant growth potential. If you are a mid-senior AI Engineer with a strong background in Python and production ML systems, this role offers an exciting opportunity to contribute to innovative projects at Lorven Technologies. Apply now to join a forward-thinking team and shape the future of AI.

Quick Overview

Work Type
Hybrid
Level
Mid Senior

Job Description

Hi

Our client is looking for an AI Engineer (GenAI / Agentic AI / LLM Engineer) project in NY/NJ or Dallas, TX below is the detailed requirement.

 

Job Title: AI Engineer (GenAI / Agentic AI / LLM Engineer)
Location: NY/NJ, Dallas, TX

Required Skills: GenAI, Agentic AI, LLMs, RAG, Production ML Systems, and Python


Job description:

 

  • Bachelor’s degree in computer science, Information Technology, or a related field
  • Developed Agentic AI applications using Python, LLMs, and RAG for enterprise automation.
  • Built scalable Retrieval-Augmented Generation (RAG) pipelines using vector databases and embedding models.
  • Designed AI agents with tool calling, function execution, and secure workflow orchestration.
  • Integrated OpenAI, Claude, Gemini, and Llama models into production applications.
  • Implemented prompt engineering, response validation, self-correction, and evaluation frameworks for LLM applications.
  • Built production-grade ML pipelines including model deployment, monitoring, inference, and continuous evaluation.
  • Integrated AI services with observability, incident management, deployment automation, and production monitoring platforms.
  • Deployed scalable AI applications on AWS using Lambda, EKS, SageMaker, S3, DynamoDB, and Terraform.
  • Implemented AI governance, guardrails, policy enforcement, rollback strategies, and production safety controls.
  • Optimized inference cost and latency using prompt optimization, caching, batching, streaming, and model routing techniques.

Skills

DynamoDB
AWS
LLM
Python
Terraform

Similar jobs