Senior Generative AI Engineer – Voice & LLMs, AWS

MACHINE LEARNING TECHNOLOGIES LLC; Frisco (TX); On-site; USD 150,000 - 190,000; Full time

Job summary

MACHINE LEARNING TECHNOLOGIES LLC in Frisco, TX seeks a Generative AI Engineer to design, build, and deploy production-ready AI agents and voice-enabled apps for government-related projects.

You will develop scalable back-end services using Python, OOP, and async patterns, integrate with enterprise systems, and implement prompt engineering, RAG, and guardrails, with Docker/Kubernetes and AWS.

Qualifications

• Minimum 5+ years of software engineering experience with strong Python development.
• Proficient in Python, OOP, asynchronous programming, and automated testing.
• Experience in conversational AI and voice AI agent development.
• Experience with Speech-to-Text (STT) and Text-to-Speech (TTS).
• Familiar with Large Language Models (LLMs), LangChain, LangGraph, and AI agent orchestration.
• Experience with Retrieval-Augmented Generation (RAG) and vector search.

Responsibilities

• Design, develop, test, and deploy production-ready AI agents and voice-enabled applications.
• Build scalable backend applications using Python, OOP, and asynchronous programming.
• Develop multi-turn conversational workflows with context management, memory, and handoff capabilities.
• Implement AI agent orchestration using LangChain, LangGraph, and LLMs.
• Develop voice AI solutions with STT and TTS.
• Integrate AI agents with enterprise systems, APIs, and contact center platforms.
• Build secure REST APIs, microservices, and event-driven architectures.
• Develop and deploy scalable cloud applications using AWS services and serverless architecture.
• Work with Docker, Kubernetes, and containerized deployment environments.
• Integrate relational, NoSQL, and vector databases for data storage and AI-powered retrieval.
• Implement AI guardrails, security controls, error handling, and responsible AI practices.
• Develop automated unit, integration, performance, and conversational regression tests.
• Configure CI/CD pipelines for continuous integration, deployment, and application delivery.
• Monitor application performance, troubleshoot production issues, and improve system reliability.
• Collaborate with AI/ML engineers, cloud architects, and enterprise technology teams to deliver AI automation solutions.

Skills

Python development

OOP

Asynchronous programming

Automated testing

Conversational AI

Voice AI

Prompt engineering

AI agent orchestration

LangChain

LLMs

RAG

AWS

REST APIs

Docker

Kubernetes

Vector databases

Tools

LangChain

LangGraph

AWS

Docker

Kubernetes

REST APIs

Microservices

Serverless Architecture

Vector databases

CI/CD

Job description

MACHINE LEARNING TECHNOLOGIES LLC in Frisco, TX seeks a Generative AI Engineer to design, build, and deploy production-ready AI agents and voice-enabled apps for government-related projects.

You will develop scalable back-end services using Python, OOP, and async patterns, integrate with enterprise systems, and implement prompt engineering, RAG, and guardrails, with Docker/Kubernetes and AWS.