Services
Voice AI
Real-time voice pipelines — voice activity detection, speech-to-text, LLM orchestration and text-to-speech — engineered for latency and operating cost.
What you get
- VAD → STT → LLM → TTS pipeline design
- Provider-agnostic speech layer
- Conversation memory and orchestration
- Cost and latency optimization
How I work
- 1
Scope & architecture
Clarify the goal, constraints and success metrics, then design the simplest architecture that meets them.
- 2
Build & evaluate
Ship in small increments with tests and evaluation, keeping performance, security and cost measurable.
- 3
Deploy & operate
Containerize, automate the pipeline and deploy to production — then monitor and improve.
Technologies
Examples from my work
Voice AI · Infrastructure
Voice AI Infrastructure
Real-time voice pipeline combining voice activity detection, speech-to-text, LLM orchestration, conversational memory and text-to-speech.
Read the case studyAI Agents · Recruitment
AI Interview Agent
An AI system that conducts interviews, processes candidate answers, evaluates performance and generates structured feedback.
Read the case study
Frequently asked questions
Can you deliver Voice AI remotely?+
Yes. I'm based in Casablanca, Morocco and work with teams remotely and internationally, in English and French.
Which technologies do you use?+
Mainly Python, LLM and Docker — chosen to fit the project rather than the other way around.
Do you have examples?+
Yes — see the case studies: Voice AI Infrastructure and AI Interview Agent.
How do we start?+
Send a message on LinkedIn or Malt with a short description of the project; we'll scope it together before any commitment.
Abdelkabir El Bahmadi · Software / AI Engineer · Casablanca
Services
Have a project in mind?
Open to remote and international opportunities — engineering roles, AI projects and product collaborations.