AI/ML Engineer – LLM & Voice Pipeline (w/m/d) - hands on experience in hands-on AI/ML, LangChain/LangGraph, Azure, ASR engine

Luxoft Germany; Ingolstadt; On-site; EUR 85,000 - 110,000; Full time

Job summary

Luxoft Germany is leading an in-vehicle AI initiative to advance voice assistants with AI model integration on the Azure platform. The role focuses on building robust RAG pipelines, ASR/TTS integration, and empathic dialogue components for edge devices in automotive contexts.

You will collaborate with cross-functional teams to deploy production-grade AI capabilities, optimize latency, and ensure safety and evaluation metrics across BLEU/WER/CER in on-device deployments.

Qualifications

• 3+ years of hands-on AI/ML engineering in production environments.
• Strong Python skills; practical experience with LLM frameworks.
• Experience designing and building RAG systems (embedding models, chunking, retrieval eval).
• Familiarity with Azure OpenAI Service or OpenAI API and prompt engineering best practices.
• Experience with at least one ASR engine and a TTS system.
• English proficiency at B2 level or higher.

Responsibilities

• Design, implement, and optimize RAG pipelines integrating Azure AI Search, vector stores, and LLM endpoints.
• Develop and maintain ASR and TTS integration modules with pyAudio and librosa.
• Create LLM prompt chains, evaluation frameworks, and safety/alignment guardrails for in-vehicle dialogue.
• Prototype few-shot adapters, intent classification, and empathic dialogue; transition prototypes to production.
• Collaborate with backend engineers to connect the AI layer with streaming infrastructure (FastAPI/Kafka).
• Contribute to edge AI components including on-device inference, model quantization, and latency management.
• Monitor model quality metrics (BLEU, WER, CER, faithfulness) via continuous evaluation pipelines.
• Participate in code reviews with cross-functional teams including customer ML engineers.

Skills

AI/ML engineering

Python

RAG systems

Prompt engineering

English (B2+)

LLM frameworks

Education

Tools

LangChain

LangGraph

Azure OpenAI / OpenAI API

pyAudio

librosa

ONNX / TensorRT

Job description

Project description

Our client is advancing its in-vehicle voice assistant into an intelligent, AI-powered companion. Since 2024, they have been incorporating large-language-model capabilities (Azure OpenAI / ChatGPT) into vehicles equipped with the MIB3 infotainment system, with new E³-architecture models featuring enhanced voice functions from the factory. The AIME (AI Model Engine) backend program supports this development over a multi-year timeline, addressing natural-language dialogue, empathic communication, and the complete cloud-edge data pipeline. DXC Luxoft serves as the end-to-end delivery partner, collaborating closely with the client’s engineers within a joint product team on the Azure platform (AKS, Azure OpenAI, Managed Identity, Azure Monitor, Azure DevOps).

Responsibilities

• Design, implement, and optimize RAG pipelines integrating Azure AI Search, vector stores, and LLM completion endpoints


• Develop and maintain ASR and TTS integration modules, including audio pre- and post-processing using pyAudio and librosa


• Create LLM prompt chains, evaluation frameworks, and safety/alignment 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 develop the FastAPI/Kafka interface connecting the AI layer with the streaming infrastructure


• Contribute to edge AI components including on-device inference, model quantization, and latency management for in-vehicle use


• Monitor and enhance model quality metrics including BLEU, WER, CER, and faithfulness via continuous evaluation pipelines.


• Participate in code reviews with cross-functional teams, including customer ML engineers.

Skills

Must have

• 3+ years of hands-on AI/ML engineering in production environments


• Strong Python skills; experience with LLM frameworks: LangChain, LangGraph, or equivalent


• Practical experience building RAG systems (chunking strategies, embedding models, retrieval evaluation)


• Familiarity with Azure OpenAI Service or OpenAI API; prompt engineering best practices


• Experience with at least one ASR engine (Whisper, Azure Speech, or equivalent) and a TTS system


• English B2 or above

Nice to have Skills

• pyAudio / librosa audio signal processing


• Edge inference: ONNX, TensorRT, or on-device model deployment


• Automotive in-vehicle speech processing context (noise cancellation, far-field microphones)


• Experience with LLM evaluation frameworks (DeepEval, Ragas, PromptFlow).


• German language skills.

Languages:

English - C1 Fluent