AI Platform Engineer — On-Prem LLMs & NVIDIA GPUs

Understand Tech Inc.; Frontignan; On-site; EUR 60,000 - 90,000; Full time

Job summary

Understand Tech Inc. is expanding its AI platform with on-site deployments in Frontignan, France. We seek an AI engineer who codes, ships and talks to customers, owning scope from roadmap to support.

You will build and operate AI components, run inference on NVIDIA GPUs, and ensure governance and GDPR compliance for enterprise clients. You will own the data architecture, prototype with RAG pipelines, and deliver demos with sales.

Qualifications

• 3+ years of experience in machine learning or AI engineering.
• At least one LLM project shipped to production.
• You show ownership, autonomy and urgency.
• Strong Python, FastAPI and Git skills.
• You know how to build a RAG pipeline end-to-end.

Responsibilities

• Build the platform's AI components: RAG, embeddings, document ingestion pipelines, prompts and agent chains, answer evaluation.
• Run and optimize LLM inference on NVIDIA GPUs: deploy and tune inference engines (vLLM, TensorRT-LLM, NIM, Ollama), quantization, batching, KV cache, throughput and latency on single machines and multi-GPU racks.
• Operate models in production on customer hardware: model lifecycle, versioning, monitoring, GPU usage, upgrades without downtime.
• Work on the data architecture: vector stores, migration to pgvector, model selection (Nemotron, Qwen, gpt-oss, etc.) and benchmarking.
• Own your product: roadmap, trade-offs, GitHub ticket prioritization, sign-off on what goes to production.
• Handle technical support for a few accounts: reproduce a bug reported on Slack, find the root cause, fix it or get it fixed, reply to the customer.
• Build demos and POCs for prospects with the sales team.
• Write the documentation for what you ship, for the team and for customers.

Skills

Python

FastAPI

Git

LLM deployment

GPU optimization

Multilingual communication

Tools

NVIDIA GPUs

vLLM

TensorRT-LLM

Ollama

PostgreSQL

MongoDB

Firebase

Docker

Kubernetes

AWS

GCP

pgvector

Job description

Understand Tech Inc. is expanding its AI platform with on-site deployments in Frontignan, France. We seek an AI engineer who codes, ships and talks to customers, owning scope from roadmap to support.

You will build and operate AI components, run inference on NVIDIA GPUs, and ensure governance and GDPR compliance for enterprise clients. You will own the data architecture, prototype with RAG pipelines, and deliver demos with sales.