Haystack
← Back to Jobs
Technology
VC

AI/ML Engineer Generative AI & RAG

VST Consulting, IncPlano, TX🇺🇸United StatesPosted 31 Aug 2026

Why This Role Stands Out

This hybrid role offers you the chance to build cutting-edge generative AI applications and RAG systems, working with LLMs and vector databases to drive innovation. You'll thrive here if you have hands-on experience with frameworks like LangChain and Azure AI services, eager to collaborate and develop impactful AI solutions. Apply now to join a forward-thinking team and advance your skills in a dynamic field.

Quick Overview

Seniority
Mid Senior
Work mode
Hybrid
Location
Plano, TX, United States
Posted
23 hours ago
MicroservicesMachine LearningAzureDatabricksGPTGenerative AIGitLLMPythonREST

Job Description

Role Name: AI/ML Engineer – Generative AI & RAG
Location: Plano, TX
Employment Type: Full-Time
Experience: 4+ Years
Salary: Up to $90,000 USD
Relocation: Relocation is Fine

Job Summary

We are seeking an experienced AI/ML Engineer to design, develop, and deploy Generative AI applications, with a strong focus on Retrieval-Augmented Generation (RAG) and agentic workflows. The ideal candidate will have hands-on experience building production-grade AI applications using LLMs, vector databases, LangChain, agent frameworks, and Azure AI services.

The candidate will work closely with data engineering and application teams to integrate enterprise data with advanced AI reasoning and automation capabilities while ensuring scalability, performance, accuracy, and reliability.

Key Responsibilities

Design and build agentic AI applications using LangChain or similar frameworks, integrating enterprise data sources such as Azure Databricks, documents, APIs, and databases.

Build, implement, and optimize RAG architectures and vector databases for AI agents using Azure AI Search or similar technologies.

Integrate Azure OpenAI, GPT models, and other LLMs into enterprise applications.

Develop effective prompt engineering and optimization strategies to improve LLM accuracy and performance.

Implement AI evaluation, monitoring, and guardrails to address accuracy, bias, hallucinations, and overall model reliability.

Collaborate with Data Engineers, Software Engineers, and Application Teams to integrate AI solutions into production environments.

Optimize AI applications for performance, latency, scalability, and cost in large-scale deployments.

Develop and integrate APIs and microservices for AI/ML applications.

Work with emerging technologies such as MCP (Model Context Protocol) and agent orchestration patterns.

Communicate technical concepts, insights, and AI solution capabilities effectively to both technical and non-technical stakeholders.

Required Qualifications

4+ years of experience in AI/ML Engineering, Data Science, Machine Learning, or a related field.

Strong hands-on experience with Python as a core development language.

Hands-on experience with Generative AI, LLMs, RAG, AI Agents, and Vector Databases.

Strong experience with LangChain or similar LLM/agent frameworks.

Experience with Azure AI ecosystem, including Azure OpenAI and Azure AI Search.

Experience working with data from Azure Databricks or similar relational/data platforms.

Strong understanding of RAG architecture, vector search, embeddings, LLM orchestration, and agentic workflows.

Experience with Git and GitHub for source control and collaborative development.

Experience developing and integrating REST APIs and microservices.

Familiarity with MCP (Model Context Protocol) and scalable AI system design.

Understanding of LLM evaluation, monitoring, prompt engineering, guardrails, hallucination mitigation, and responsible AI practices.

Strong analytical, problem-solving, and communication skills.

Similar jobs