Senior GenAI / Voice AI Engineer | Speech-to-Speech | ServiceNow Portal Start | December

Project overview

Dear Freelancers,

For one of our best clients, we are looking for an experienced GenAI / Voice AI Engineer (m/f/d) to further develop an AI-based real-time voice assistant in the ServicePortal (ServiceNow).

The goal of the project is to further develop a successfully piloted Proof of Concept (PoC), integrate it into the existing system landscape, and transition it to productive regular operation. The voice assistant enables employees to describe their IT concerns via voice and receive immediate support.

Responsibilities

• Further development and productive implementation of a real-time voice assistant based on Speech-to-Speech models
• Integration of the voice assistant into the existing ServicePortal and connection to ServiceNow
• Optimization of voice quality, especially for technical terms, pronunciation, and background noise
• Improvement of prompt engineering, knowledge retrieval, and response quality
• Technical collaboration with the internal development team and knowledge transfer

Requirements

• Several years of practical experience in software development with a focus on GenAI and LLM-based applications
• Practical experience with Speech-to-Speech models, real-time streaming, and WebSockets
• Confident use of AI-supported software development, especially tools like Claude Code
• Sound knowledge in prompt engineering, retrieval, and knowledge-based AI applications
• Experience with cloud technologies (ideally GCP), Kubernetes, and containerized applications
• Experience in API development, system integration, and authentication

Nice to have

Note: Availability of 3–5 days per week is sufficient. In December, the workload may be temporarily lower due to project initialization and internal vacation times.

Is this project interesting for you? Then please get in touch with your current CV and details of your hourly rate and availability. I will get back to you immediately.

Best regards

Bacel Issa

• Experience with Gemini Live or comparable real-time models
• Knowledge of ServiceNow, especially ServicePortal and Knowledge Base
• Experience with Azure Kubernetes Service (AKS)
• Knowledge of audio signal processing and evaluation of voice and LLM applications

Project details

min. daily in December 2026/ January at the latest

6 months

3–5 days/week (60–100%)

Remote / On-site: Mainly Remote

GR Stuttgart

• Start: ab sofort
• Duration: 6 Monate
• Remote: remote
• Location: Stuttgart, Deutschland, DE
• Languages: German