Staff AI Engineer - Agentic Shopping Architect

Picnic; Amsterdam; On-site; EUR 120,000 - 180,000; Full time

Benefits offered by this job

Health insurance discount

Bike plan

Relocation support

Lunch & snacks

25 holidays

Job summary

Picnic is seeking a Staff AI Engineer to lead the technical direction for agentic shopping experiences at scale. You will own architecture, model strategy, and evaluation patterns for multi-turn conversational systems powering the Picnic shopping assistant.

You will build production-grade RAG, context management, and monitoring loops while mentoring engineers to ship impactful features that delight millions of households and customers.

Qualifications

• Proven track record of taking complex multi-turn conversational AI systems from architectural design to high-scale production.
• Experience training, fine-tuning, and optimizing open-weight LLMs for production deployment.
• Hands-on expertise building production RAG systems, context management, and state handling for multi-turn dialogues.
• Experience designing robust evaluation loops, continuous monitoring systems, and automated safety/guardrail mechanisms for customer-facing applications.
• Demonstrated ability to lead technical direction, perform design reviews, and mentor engineering teams without relying on hierarchy.
• Strong Python skills and demonstrated ability to productionize model, orchestration, retrieval, evaluation and inference tooling; familiarity with PyTorch, LangGraph, vLLM, Pydantic AI, Qdrant or DeepEval is useful.

Responsibilities

• Lead the technical direction for agentic shopping experiences that help millions of people plan and shop effortlessly.
• Architect multi-turn conversational systems balancing latency, safety guardrails, and inference costs; mentor engineers across the org.
• Drive a fast-paced, iterative engineering cadence; build prototypes and write production code when needed.
• Design and implement systems architectures for multi-turn conversational agents using open-weight models and techniques like fine-tuning, distillation, and RAG.
• Establish offline and online evaluation for mission completion, basket correctness, user effort, and safety.
• Collaborate with product, design, and product teams to define trade-offs and ensure a safe user experience.

Skills

Multi-turn AI

Open-weight LLMs

RAG systems

Context management

Evaluation loops

Safety guardrails

Python

Education

Degree in CS/AI

Tools

PyTorch

LangGraph

vLLM

Pydantic AI

Qdrant

DeepEval

Job description

Picnic is seeking a Staff AI Engineer to lead the technical direction for agentic shopping experiences at scale. You will own architecture, model strategy, and evaluation patterns for multi-turn conversational systems powering the Picnic shopping assistant.

You will build production-grade RAG, context management, and monitoring loops while mentoring engineers to ship impactful features that delight millions of households and customers.