AI Vehicle Backend Architect for LLM-Driven Cockpit

Luxoft; Polska; On-site; PLN 320,000 - 520,000; Full time

Job summary

Luxoft, in collaboration with a client, is expanding its in-vehicle AI platform by architecting the backend service that delivers streaming ASR→LLM→TTS, guardrails, and tool integrations. This role is responsible for multi-year architectural evolution across vehicle generations.

You will own API contracts, orchestration, and observability, ensuring high availability and backward compatibility while integrating Azure OpenAI and LangGraph. A strong backend and AI-ops background is essential.

Qualifications

• 8+ years in backend/distributed systems engineering, with 3+ years as architect or technical lead.
• Expert Python: FastAPI, async, and streaming architectures.
• Proven experience architecting LLM-based production systems — orchestration of tool- and agent-based workflows with LangChain / LangGraph or equivalent, prompt strategies, structured outputs, LLM constraint handling and guard-railing.
• Azure OpenAI Service or OpenAI API in production, including model version migration and the compatibility problems it creates.
• Strong API and interface design: REST and gRPC/protobuf, versioning and backward compatibility strategies, OAuth2 and mTLS for secure service-to-service communication.
• PostgreSQL at depth: schema design, tuning, migrations (Alembic); plus working experience with embeddings and vector search for RAG (pgvector or equivalent).
• Kubernetes / container orchestration (deployment, scaling, secrets/config, networking, load balancing) and Azure cloud architecture (AKS or Container Apps, Managed Identity, Key Vault, Monitor).
• Infrastructure as Code with Terraform: reusable modules, environment separation, remote state and locking, CI/CD integration, lifecycle management.
• Demonstrable responsibility for running a production service: monitoring, alerting, distributed tracing with OpenTelemetry, incident and problem management, patch and release management, latency and cost optimization against defined targets.

Responsibilities

• Own and evolve the backend service architecture for routing and orchestration.
• Define and govern the interface concept between vehicle, LLM, tools, and agents — the formal contract layer, its versioning strategy, and its evolution across vehicle generations.
• Architect the vehicle-facing REST and gRPC APIs and related tech.
• Design streaming architecture for real-time ASR and TTS with proper handling.
• Own LLM integration layer with prompts and guardrails.
• Design agent orchestration for multi-intent routing.
• Architect tool and agent integrations across navigation, media, queries, calendar.
• Define RAG/persistence architecture including vector stores.
• Produce scaling/load concepts and security/compliance per automotive standards.
• Own observability end-to-end including OpenTelemetry and Azure Monitor.
• Maintain backward compatibility for vehicle generations.
• Set engineering standards: CI/CD on Azure DevOps and GitHub, Terraform modules.
• Collaborate with client architects and document in Confluence.

Skills

Backend architecture

Python (FastAPI)

Streaming architectures

LLM orchestration

Azure/OpenAI production

API design (REST/gRPC)

PostgreSQL & embeddings

Kubernetes/Azure

Terraform IaC

Observability/OpenTelemetry

Tools

LangGraph

LangChain

pgvector

Alembic

Terraform

AKS

Azure Monitor

OpenTelemetry

Job description

Luxoft, in collaboration with a client, is expanding its in-vehicle AI platform by architecting the backend service that delivers streaming ASR→LLM→TTS, guardrails, and tool integrations. This role is responsible for multi-year architectural evolution across vehicle generations.

You will own API contracts, orchestration, and observability, ensuring high availability and backward compatibility while integrating Azure OpenAI and LangGraph. A strong backend and AI-ops background is essential.