AI Edge Solution Architect – Edge/Cloud Voice AI

Project description

Our client is advancing its in-vehicle voice assistant into an intelligent, AI-powered companion. Large-language-model capabilities (Azure OpenAI / ChatGPT) have been running in production across vehicles. The goal of the project is to develop a backend which is the cloud AI orchestration service behind this: it receives requests from the vehicle, routes them, orchestrates the LLM, tool services and agents, and returns an answer or action to the car. DXC Luxoft serves as the end-to-end delivery partner, working in a joint product team with the client's engineers on the Azure platform. This is the series development and operations work package - a live platform serving a large vehicle fleet, which extends sprint by sprint the backend features while availability and backward compatibility are maintained. New capability in the pipeline includes streaming across the full ASR → LLM → TTS chain, barge-in, multi-intent handling, a guardrails layer for deterministic vehicle-safe answers, agent routing and new tool integrations. The role is Technical Lead and

Location

Lead for the engineering team. It is a hands-on delivery leadership role: the person is accountable for what the team ships, for the service running inside its availability and incident targets, and for the technical growth of the location.

Work package A — Concept development & pre-development (research, evaluation, prototyping)

Responsibilities

• Own the system architecture for hybrid (cloud/edge) voice assistant systems — define the edge/cloud allocation model, routing criteria, and the port/adapter boundaries that allow functions to move between cloud and vehicle without redesign.
• Design and oversee end-to-end prototype pipelines (ASR → LLM → TTS), including integration into early vehicle platforms (E³, SDV) and test operation in lab and driving environments.
• Drive evaluation and benchmarking of base components: on-device ASR for edge hardware, modern TTS models (latency, robustness, audio quality, energy efficiency), and candidate LLMs for dialogue-based assistant functions via Azure AI Foundry.
• Define RAG architectures for improved knowledge coverage and robustness, including embedding strategies and small-scale vector stores for specific automotive use cases.
• Architect the embedded/edge AI optimisation workstream: quantisation, pruning and distillation for ARM/DSP/NPU targets, with explicit attention to memory footprint, energy consumption, wake-word efficiency and thermal behaviour.
• Shape the research agenda for future key technologies — continual learning and on-device model adaptation (anti-drift), multimodal interaction (speech + image + vehicle sensor data), emotion and sentiment recognition, privacy-compliant on-device personalisation and long-term memory, multi-speaker handling, speaker identification and anti-spoofing.
• Embed safety, security and privacy mechanisms into concepts from the start (differential privacy, secure enclaves, automotive security standards) and ensure interoperability with vehicle architectures (SOA, microservices, zonal architecture).
• Apply and enforce hexagonal architecture as the structural standard, so prototypes are transferable into series development rather than thrown away.
• Produce the technical concepts, architecture decision records and evaluation reports that hand research results over to the series development work package — and defend them in review with the client's architects.
• Lead the offshore engineering team as

Location

Lead: technical direction for AI/ML and AI Ops engineers, code and design review standards, work breakdown and estimation across a high-throughput ticket flow (~30 tickets/sprint, sizes S/M/L), onboarding and skills growth.

• Act as the offshore technical counterpart to the onshore solution architect and client engineering teams; run technical alignment across time zones and represent the location in architecture boards and sprint ceremonies.

Skills

Must have

• Edge / on-device AI: model optimisation (quantisation, pruning, distillation) and deployment to constrained hardware — ARM, DSP, NPU, or mobile/embedded equivalents.
• Expert Python.
• Hands-on with LLM frameworks in production: LangChain, LangGraph or equivalent.
• 3+ years as architect or technical lead, with end-to-end ownership of a system's design (within 8+ years total engineering experience).
• Track record of taking AI/ML or LLM systems from prototype into production — not research-only.
• Practical experience building RAG systems: embedding models, vector stores, retrieval evaluation.
• Azure OpenAI Service or OpenAI API in practice, plus Azure cloud (AKS or Container Apps).
• Integration experience with at least one ASR or TTS engine (Whisper, Azure Speech, Cerence or equivalent).
• Experience leading a distributed engineering team (5–10 engineers) in Scrum/Kanban.
• English C1, and willingness to travel to Germany for workshops, architecture reviews and prototype test campaigns.

Nice to have

• Hexagonal / ports-and-adapters architecture and API design (REST, gRPC, protobuf, OAuth2) — the client mandates this architecture style, so the candidate must be willing to adopt it quickly.
• Automotive / in-vehicle software context: infotainment platforms (MIB3, E³, SDV), Android Automotive / AAOS, AIDL, Viwi, vehicle telemetry services, SOA or zonal E/E architectures.
• In-vehicle speech processing specifics: noise cancellation, far-field microphones, wake-word engines, barge-in, multi-speaker cabin scenarios.
• Edge inference toolchains: ONNX Runtime, TensorRT, TFLite, OpenVINO; audio signal processing with pyAudio / librosa / pydub.
• Observability and evaluation for LLM systems: LangFuse, OpenTelemetry, and evaluation frameworks (DeepEval, Ragas, PromptFlow); quality metrics such as BLEU, WER, CER, faithfulness and hallucination rate.
• Commercial automotive speech/emotion stacks (Cerence, HumeAI) and Google TTS.
• Privacy-preserving ML: differential privacy, federated/aggregate learning signals, secure enclaves, on-device personalisation.
• Speaker identification and anti-spoofing.
• Data/persistence breadth: PostgreSQL + pgvector, MongoDB, CosmosDB; IaC with Terraform/Terragrunt.
• Awareness of automotive quality and security frameworks (A-SPICE, ISO/SAE 21434, TISAX) and of EU AI Act implications for AI systems.
• German language skills.

Other

Languages

English: C1 Advanced,German: B2 Upper Intermediate

Seniority

Senior

Remote Germany, Germany

Req. VR-125473

Software/System Architecture

Automotive Industry

09/10/2026

Req. VR-125473

Apply for AI Edge Solution Architect – Edge/Cloud Voice AI in Remote Germany

*Indicates a required field

First name

Last name

Email

Your country

Your City

Phone

Specialization

Attach your resume (max file size 1MB; allowed extensions: doc, txt, pdf, docx)

Upload resume

Number of years of experience in the specialization you are applying for

What are your monthly gross salary expectations?

Read Explanatory Notes

Under the terms of your specific consent or to perform our obligations under a contract with you, as applicable, we, Luxoft Holding Inc. will manually and electronically process your personal data, specifically your first name, last name, phone number, e-mail address and other data you provide us through this form.

Within this context, we process personal data only for the specific purpose(s) indicated in the individual consent language or other notices provided below.

We will – insofar as reasonably necessary for the purpose you have agreed to and within the scope of applicable laws – transfer your personal data to other entities within the Luxoft Group and to the group of third party recipients listed in our Privacy Notice. Such Recipients can be located outside the European Union (EU) and/or the European Economic Area (EEA) (“Third Countries”). The Third Countries concerned, e.g. the USA, may not have the level of data protection that you enjoy e.g under the GDPR. This can result in disadvantages such as an impeded enforcement of data subjects’ rights, a lack of control over further processing and access by state authorities. You may only have limited legal remedies against this. Insofar our transfer of your personal data to recipients in Third Countries is not covered by an adequacy decision of the EU Commission, we achieve an adequate level of data protection as further detailed out in our Privacy Notice.

With your consent, we personalise marketing communications to you by way of carrying out marketing research analysis, analysing the surfing-behaviour of our website visitors and to adjust it to their detected tendencies, as well as to plan more efficient future marketing activities. This personalised marketing does not include any automated decision-making activities.

Further information on how we process personal data in general is available in our Privacy Notice. You may withdraw any given consent at any time. The withdrawal of your consent(s) will not a