ai engineer for agentic shopping

Picnic operates a sustainable grocery retail business with a direct customer relationship, live grocery assortment, and an operational system that manages orders from planning through delivery. The company is developing an AI-powered shopping assistant for household grocery planning and shopping.

• Lead the technical direction for agentic shopping experiences that help millions of people plan and shop effortlessly;
• Lead the system architecture for multi-turn conversational agents while balancing latency, safety guardrails, and inference costs;
• Technically mentor engineers across the organization in building production-grade agentic systems;
• Drive a fast-paced, iterative engineering cadence;
• Build initial prototypes, establish architectural patterns, and write production code when necessary to unblock complex technical challenges;
• Design and implement system architectures for multi-turn conversational agents using open-weight models, fine-tuning, distillation, and RAG;
• Establish continuous offline and online evaluation for mission completion, basket correctness, customer effort, clarification quality, acceptance and corrections, safety, reliability, latency, and cost;
• Collaborate with product and design teams to define technical trade-offs, align on agent capabilities, and ensure a seamless, safe user experience.

• 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 and guardrail mechanisms for customer-facing applications;
• Ability to lead technical direction, perform design reviews, and mentor engineering teams without relying on hierarchy;
• Strong Python skills and the ability to choose and productionize appropriate model, orchestration, retrieval, evaluation, and inference tooling;
• Experience with tools such as PyTorch, LangGraph, vLLM, Pydantic AI, Qdrant, or DeepEval, or similar framework tools;
• Nice to have: Experience taking retrieval, ranking, or recommendation models from problem definition to measurable production impact, in-depth expertise in deep learning for sequence modelling, representation learning, or retrieval and ranking, a degree in Computer Science, AI, or a related field, a PhD, open-source contributions, or peer-reviewed research.

• Team includes more than 80 nationalities across 3 countries;
• Startup environment with freedom to drive personal projects and create visible impact;
• Fresh lunches, coffee, and snacks provided at the offices;
• 5%–15% Discount on CZ health insurance packages;
• Discounted rent-to-own new or electric bicycles through Lease a Bike;
• Relocation support is available, including flight costs for the employee and their partner and children, first month's rent, moving costs up to €2000, and assistance with the 30% tax ruling setup and application;
• 25 Holidays, travel expenses, a pension plan, and company-provided phone and laptop.