AI Edge Solution Architect - Edge/Cloud Voice AI

Luxoft; Deutschland; On-site; EUR 90,000 - 130,000; Full time

Job summary

Luxoft seeks a Technical Lead and Location Lead to steer a cross-functional team building a cloud/edge voice assistant backend and orchestration platform. You will own architecture, drive end-to-end pipelines (ASR → LLM → TTS) and ensure delivery within availability targets.

The role requires hands-on leadership, strong AI/ML background, and travel to Germany for collaboration with client teams and workshops.

Qualifications

• Edge AI optimization and deployment to constrained hardware (ARM/DSP/NPU).
• Hands-on with production-ready LLM frameworks (LangChain or equivalent).
• 8+ years engineering experience with 3+ years as architect/lead.
• Track record of moving AI/ML/LLM from prototype to production.
• Practical experience building RAG systems with embeddings and vector stores.
• Azure OpenAI Service or OpenAI API in practice, plus Azure cloud.
• Experience integrating with ASR or TTS engines (Whisper, Azure Speech, Cerence).
• Experience leading a distributed engineering team (5–10) in Scrum/Kanban.
• English C1 and willingness to travel to Germany for workshops.

Responsibilities

• Own the architecture for hybrid cloud/edge voice systems and edge/cloud boundaries.
• Design end-to-end pipelines (ASR → LLM → TTS) and test in lab/driving environments.
• Drive evaluation of base components: on-device ASR, TTS, and LLMs.
• Define RAG architectures with embeddings and vector stores for automotive use cases.
• Architect embedded/edge AI optimization for ARM/DSP/NPU targets.
• Shape research agenda for on-device learning, multimodal interaction, privacy.
• Embed safety, security and privacy from the start and ensure interoperability.
• Enforce hexagonal architecture to enable transfer to series development.
• Lead offshore location team; align with onshore solution architect and client.
• Represent location in architecture boards and sprint ceremonies.

Skills

Edge AI optimization

LangChain/LLM frameworks

Architect/lead

Production AI/ML

RAG systems

Azure OpenAI / Azure

ASR/TTS integration

Distributed leadership

English proficiency

Tools

ONNX Runtime

TensorRT

TFLite

OpenVINO

pyAudio

librosa

pydub

Job 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.

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.
• 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.
• 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.