AI/ML Engineer – LLM & Voice Pipeline

About the role

We are looking for an experienced AI/ML Engineer to join a joint product team that is advancing an in‑vehicle voice assistant into an intelligent, AI‑powered companion. The role focuses on building large‑language‑model (LLM) and voice processing pipelines on Azure for automotive applications.

Key responsibilities

• Design, implement and optimise Retrieval‑Augmented Generation (RAG) pipelines using Azure AI Search, vector stores and LLM completion endpoints.
• Develop and maintain ASR and TTS integration modules, handling audio pre‑ and post‑processing with pyAudio and librosa.
• Create LLM prompt chains, evaluation frameworks and safety guardrails for in‑vehicle dialogue scenarios.
• Prototype AI capabilities such as few‑shot adapters, intent classification and empathic dialogue, then transition prototypes to production.
• Collaborate with backend engineers to build FastAPI/Kafka interfaces connecting the AI layer with streaming infrastructure.
• Contribute to edge AI components, including on‑device inference, model quantisation and latency management.
• Monitor and improve model quality metrics (BLEU, WER, CER, faithfulness) via continuous evaluation pipelines.

Required profile

• Minimum 3 + years of hands‑on AI/ML engineering experience in production environments.
• Strong Python programming skills.
• Proficiency in English (B2 or above); German language skills are a plus.
• Senior‑level expertise, as indicated by the seniority label.

Required skills

• Python
• LangChain or LangGraph (LLM frameworks)
• Azure OpenAI Service / OpenAI API
• Retrieval‑Augmented Generation (RAG) systems
• ASR engines (e.g., Whisper, Azure Speech)
• TTS systems
• pyAudio, librosa (audio signal processing)
• FastAPI, Kafka
• Edge inference tools (ONNX, TensorRT)
• Azure platform services (AKS, Azure Monitor, Azure DevOps, Managed Identity)
• Evaluation frameworks (BLEU, WER, CER, DeepEval, Ragas, PromptFlow)