Senior Full-Stack Python/JavaScript Engineer - Automation Builder - MLOps

Discover International; Dublin; On-site; EUR 120,000 - 180,000; Full time

Job summary

Discover International in Ireland is seeking an ambitious AI Engineer to lead our AI Hub as Employee #1. You’ll build an on-prem AI sandbox on an NVIDIA DGX Spark unit and ship production-ready automations.

You’ll assemble the core stack (n8n, PostgreSQL, vector DB, Langfuse, Prometheus/Grafana, Ollama) and deploy LLM-powered agents for regulatory submissions, operations, and R&D. This is a greenfield role with fast prototyping and no legacy systems.

Qualifications

• Experience integrating LLMs via OpenAI/Anthropic/OpenRouter.
• Strong SQL and PostgreSQL experience.
• Familiarity with vector databases for embeddings.
• Experience with low-code/no-code automation platforms.
• Comfortable with Linux, Docker, and SSH.

Responsibilities

• Build on-prem AI sandbox and production automations.
• Develop core AI stack and automation platform.
• Prototype fast, fail forward, with minimal legacy.
• Deploy 5–7 production-ready automations in 2026.

Skills

LLM integration

Prompt engineering

LLM APIs

PostgreSQL

Vector databases

Caching patterns

Low-code/no-code

Docker

Linux

SSH/systemd

NVIDIA DGX hardware

Tools

n8n

Zapier/Make.com

Docker

Docker Compose

Langfuse

Prometheus

Grafana

Ollama

Job description

I'm working with a fast-moving specialty pharma group operating across 40+ markets, with deep expertise in rare diseases including haematology-oncology. They partner with manufacturers to commercialize life-saving medicines quickly and efficiently, from regulatory approval through to patient access.

Reporting to the Head of AI & Digitalisation, you will be Employee #1 in the AI Hub. Your first mission: build our on-prem AI sandbox on an NVIDIA DGX Spark unit (128 GB RAM, 4 TB SSD), then ship 5-7 production-ready AI automations in 2026. This is a greenfield role—no legacy systems, no bureaucracy, just you, the DGX box, LLM APIs, and a mandate to prototype fast and fail forward.

You will build the core stack (n8n, PostgreSQL, vector DB, Langfuse, Prometheus/Grafana, Ollama) and create LLM-powered agents for regulatory submissions, HCP targeting, pharmacovigilance, and internal ops—automations that will 3X our capacity without adding headcount.

Requirements

• LLM integration: OpenAI/Anthropic/OpenRouter APIs, prompt engineering, function calling, streaming
• Database & storage: PostgreSQL, vector DBs (Qdrant/Pinecone/Weaviate), Redis/caching patterns
• Workflow automation: n8n, Zapier, Make.com, or similar low-code/no-code platforms
• Linux/Docker: comfortable with SSH, docker-compose, systemd, basic networking