AI Chatbot Engineer

Athes Inc
United States
13 days ago

Role details

Contract type
Permanent contract
Employment type
Part-time (≤ 32 hours)
Compensation
$97,123.0 - $116,966.0
Working hours
Regular working hours
Job source

Tech stack

Application Programming Interfaces (APIs) Artificial Intelligence Linux Python (Programming Language) Performance Tuning Raspberry Pi Cloud Services Smart Devices Software Deployment Speech Recognition WebSocket Core Voice Platform
+12 more
Chatbots Large Language Models Prompt Engineering Generative AI Git Fastapi Linux Development Low Latency Speech Synthesis Restful APIs GPT Docker

Job description

We are looking for an experienced AI Engineer passionate about LLMs, voice AI, and real-time AI systems.

About the Role

As an AI Voice Agent Engineer, you will architect and build a conversational AI tutor that interacts naturally with students using speech.

You will integrate state-of-the-art Large Language Models with Speech-to-Text (STT), Text-to-Speech (TTS), memory, prompt engineering, and tool calling to create a highly engaging educational experience.

The system will operate on embedded edge hardware while maintaining low latency and high conversational quality.

Responsibilities

  • Design and develop production-ready AI voice agents
  • Build low-latency conversational pipelines
  • Integrate Speech-to-Text engines
  • Integrate Text-to-Speech engines
  • Build prompt engineering workflows
  • Implement conversation memory
  • Design agent workflows using modern LLM frameworks
  • Optimize latency for real-time conversations
  • Deploy AI models on edge devices
  • Build APIs for communication between hardware and cloud services
  • Improve tutoring quality through prompt optimization and evaluation
  • Collaborate with robotics and embedded engineers, You’ll help create an AI tutor capable of:
  • Holding natural voice conversations
  • Teaching math, science, and reading
  • Remembering previous lessons
  • Adapting to each student’s learning style
  • Answering questions in real time
  • Running on our tutoring robot with minimal latency

Tech Stack

  • Python
  • OpenAI
  • GPT-4.1 / GPT-5
  • Whisper
  • Deepgram
  • ElevenLabs
  • Cartesia
  • LangGraph
  • LangChain
  • LiveKit
  • Pipecat
  • FastAPI
  • Docker
  • Linux
  • Raspberry Pi
  • NVIDIA Jetson
  • Git
  • WebSockets

Requirements

  • Strong Python programming skills
  • Experience building AI agents using modern LLM APIs
  • Experience with OpenAI, Anthropic, or Gemini APIs
  • Experience with prompt engineering
  • Experience with Retrieval-Augmented Generation (RAG)
  • Experience integrating Speech-to-Text systems
  • Experience integrating Text-to-Speech systems
  • Experience building real-time voice applications
  • Experience with REST APIs and WebSockets
  • Experience with Linux development
  • Familiarity with Docker
  • Experience deploying applications on Raspberry Pi, NVIDIA Jetson, or similar edge devices
  • Understanding of latency optimization for AI inference

Preferred Qualifications

Experience with one or more of the following:

  • LiveKit
  • Pipecat
  • LangGraph
  • LangChain
  • LlamaIndex
  • Vapi
  • ElevenLabs
  • Deepgram
  • Whisper
  • Cartesia
  • OpenAI Realtime API
  • Google Live API
  • MCP (Model Context Protocol)
  • Robotics
  • Embedded AI

Nice to Have

  • Built production AI assistants
  • Built customer support voice agents
  • Built educational AI applications
  • Experience fine-tuning LLMs
  • Experience with on-device inference
  • Experience with TinyML or edge AI optimization

Benefits & conditions

$97,123.31 - $116,965.71 a year - Part-time

About the company

APEX Cybernetics is building the next generation of AI-powered tutoring robots for children. Our mission is to create an intelligent AI tutor capable of natural spoken conversations, personalized teaching, and running efficiently on edge devices.

Apply for this position

This job is hosted externally. Click below to view the full posting and apply.

Apply on www.indeed.com

Good distractions

Talks and stories from around this role — technically off-topic, practically not.

1:24 min

Building client-facing AI agents for engineering teams

Alfonso Graziano Alfonso Graziano · Coffee With Developers

40 sec

Generative pre-trained transformer models powering code completions

lgonta lgonta +1 · WWC 2024

6:21 min

Investigating push inefficiencies with upstream Git experts

Jonathan Creamer · Coffee With Developers

52 sec

Running persistent Linux environments directly on Windows

Ben Breard Ben Breard · WWC 2025

58 sec

Using AI agents as career and technical interview coaches

Ekaterina Kapranova Ekaterina Kapranova · WWC Europe 2026

51 sec

Assessing GPT-4o performance for pull request feedback

Merrill Lutsky Merrill Lutsky · WWC 2025

Videos

See all

Related articles

See all