Senior Artificial Intelligence Specialist

Why this role exists:

We are growing our AI team and are looking for a Senior AI / Generative AI Engineer to build and operate production-grade LLM-based systems across the platform.

This role focuses on applied Generative AI: internal AI automation, chatbots, AI assistants, and MCP-based services already used in production. You will work on top of an existing ML and data platform, building systems that are reliable, maintainable, and practical to operate.

This is a hands-on engineering role with end-to-end ownership. Not research. Not prompt-only.

What you’ll drive:

Technical Ownership

— Own LLM-based systems from design to production support.
— Design architectures for Generative AI systems (RAG, agents, tool/context serving).
— Make clear trade-offs between quality, latency, cost, and complexity.
— Set engineering standards for building and operating AI systems in production.
— Act as a technical reference point for applied GenAI.

Hands-on AI Engineering

— Build and maintain production LLM-powered systems.
— Develop chatbots and AI assistants with predictable behavior.
— Design and implement RAG pipelines (ingestion, embeddings, retrieval, generation).
— Implement agent-style workflows with tool/function calling.
— Build and integrate MCP servers or similar context/tool-serving components.
— Integrate AI systems with backend services and ML infrastructure.

Production & Reliability

— Design evaluation frameworks for LLM outputs.
— Monitor LLM behavior, system health, and costs in production.
— Address performance, scalability, and operational issues.
— Handle production incidents and contribute to long-term fixes.
— Design systems with failure modes, fallbacks, and graceful degradation.

What makes you a GR8 fit

Must-have

— Strong software engineering background.
— Proven experience building LLM-based systems in production.
— Hands-on experience with: LLMs and RAG architectures, Chatbots or conversational AI systems, Tool/function calling and agent-style patterns.
— Experience with context or tool-serving systems (MCP or similar).
— Experience integrating AI into real-time production products.
— Understanding of performance, scalability, and cost trade-offs.
— Cloud experience (preferably AWS).
— Strong engineering fundamentals (testing, debugging, reviews, observability).

Nice-to-have

— Multi-agent or workflow-based systems.
— Fine-tuning or adapting open-source LLMs.
— ML platforms / MLOps background.
— Experience operating latency- or cost-sensitive systems.
— Production incident ownership in AI systems.

Tech Stack:
Languages: Python, SQL.
LLMs: Amazon Bedrock, OpenAI, Anthropic, open-source models.
Frameworks: LangChain, LangGraph, Pydantic, Langfuse.
RAG: Embeddings, Qdrant / FAISS / OpenSearch / pgvector.
Cloud: AWS (ECS / EKS / Lambda, S3, OpenSearch).
DevOps: Docker, Git, CI/CD.

Why you’ll love working here:

Benefits Cafeteria — annual budget you allocate to:

Sports • Medical • Mental health • Home office • Languages.

Work-life & support

— Paid maternity/paternity leave + monthly childcare allowance.
— 20+ vacation days, unlimited sick leave, emergency time off.
— Remote-first + tech support + coworking compensation.
— Team events (online/offline/offsite).
— Learning culture with internal courses + growth programs.

Our culture & core values:

GR8 Tech culture is how we win — through trust, ownership, and a growth mindset. We move fast, stay curious, and keep it real, with open feedback, room to experiment, and a team that’s got your back.

FUELLED BY TRUST: we’re open, honest, and have each other’s backs.

OWN YOUR GAME: we take initiative and own what we do.

ACCELER8: we move fast, focus smart, and keep it simple.

CHALLENGE ACCEPTED: we grow through challenges and stay curious.

BULLETPROOF: we’re resilient, ready, and always have a plan.