AI Software Engineer (senior/staff level)

Joko; Barcelona; Presencial; EUR 60.000 - 90.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Flexible remote work options

Work from anywhere for up to 3 months per year

Top-market compensation

Equity options

Yearly offsite in beautiful locations

Descripción de la vacante

A leading tech company based in Barcelona seeks a Software Engineer to own the architecture of an AI assistant. This role involves evaluating AI performance, expanding capabilities, and working collaboratively with the product team. The ideal candidate has solid software engineering experience and a builder's mindset. The company offers flexible working options and a strong focus on innovation, ensuring a positive impact on consumers and empowering smarter shopping experiences.

Formación

• Proven experience in building production AI systems.
• Familiarity with LLM observability tools.
• Comfortable with frontend prototyping.

Responsabilidades

• Own the architecture of the Joko AI system.
• Design evaluation frameworks for AI performance.
• Expand tools and capabilities for AI.

Conocimientos

Software engineering experience

Knowledge of agentic frameworks

Full-stack development

Problem-solving skills

Fluent in English

Educación

AI/ML background or degree

Herramientas

LangChain

LLM APIs

Descripción del empleo

At Joko, we help consumers shop smarter. Our mission is to revolutionize shopping, empowering people to find what they need, make informed decisions, and save money.

Founded in Paris, Joko is a tech company and certified B Corp with over 90 talents across Paris, Barcelona, and New York (and beyond). More than 5 million users already save money every day at 10,000+ merchants with Joko.

From cashback and automatic coupons to price alerts and carbon tracking, we keep expanding our products to make shopping smarter. We’re now building an AI‑powered shopping assistant to help users find the best products by price, quality, and impact.

Having reached profitability in our core market, we’re now scaling globally, with a strong focus on the US.

📱 Our engineering team

Our Engineering team excels at solving cutting‑edge technical challenges with elegant solutions. With a strong focus on product innovation and design, they are shaping the future of the online shopping experience. Their ambition is to have a positive impact on the everyday lives of hundreds of millions of users around the world.

Software Engineers in the Engineering team work hand‑in‑hand with the Product team, from exploration, design, and roadmap prioritization to implementation, and deployment in production. At Joko, we have firsthand experience that teams with engineers who possess a diverse range of skills, and where engineering and product collaborate closely, can deliver a truly delightful and innovative user experience.

The Engineering team is currently growing fast to continuously innovate on all parts of our product and tech stack and to empower the revolution of the way people shop online.

🎯 What You Will Do

• Agent architecture: you will own the architecture of our agentic system — ensuring it constantly evolves, incorporates the latest advancements in the field, challenges existing assumptions, tests bold ideas, and pushes the boundaries of what our AI assistant can do.
• Evaluation & monitoring: you will design and run robust evaluation frameworks to measure Joko AI's performance, catch regressions, and build confidence before shipping to production.
• Capabilities & integrations: you will constantly expand the set of tools and capabilities that Joko AI can leverage — web search, vector search, ever‑smarter catalog lookups — making the agent more resourceful, faster, and more reliable at scale.
• Catalog & data at scale: great recommendations start with great data. Joko AI is powered by a product catalog of hundreds of millions of entries, continuously updated. You will tackle the massive challenges of ingesting, standardising, and enriching this data at scale, where AI itself plays a key role.
• Personalisation: Joko has access to uniquely rich data — bank transactions and browsing behaviour through the browser extensions — giving us unparalleled insight into user preferences and shopping patterns. You will leverage these signals to deeply understand user intent and build a truly personalised experience — making Joko AI feel like it genuinely knows what you’re looking for.
• Experimentation & prototyping: you will constantly push Joko AI forward by identifying new challenges and building new features for the agent. You will prototype fast, put early versions in users' hands, and iterate based on real feedback.
• Staying ahead: you will stay on top of the latest models, agentic frameworks, and research papers, and translate what's emerging into concrete improvements for Joko AI.
• Fine‑tuning & optimisation: you will fine‑tune models to improve quality, reduce latency, and cut costs — always with a production‑grade mindset.
• Runtime & scalability: you will iterate on the backbone and infrastructure Joko AI runs on, ensuring it handles hundreds of thousands of daily users with zero downtime and minimal latency.
• Product collaboration: we are inventing an entirely new shopping experience with Joko AI — and much of what the ideal UX looks like is still to be defined. You will work hand‑in‑hand with the Product team, exploring bold design directions, imagining what the future of AI‑assisted shopping can be, and turning that vision into reality from early concept to full rollout.

👀 Who We're Looking For

• Track record: you have solid software engineering experience, ideally building production AI systems. You have shipped things that real users rely on, and you care deeply about code quality, separation of concerns, and testing.
• Technical skills: you are deeply familiar with agentic frameworks (LangChain, LangGraph, or equivalents), LLM observability tools (LangFuse or equivalents), LLM APIs, and evaluation tooling for AI systems. An AI/ML background or degree is a strong plus, but not a blocker.
• Builder's mindset: you love building from scratch. You are not precious about your ideas — you ship, test, learn, and iterate fast.
• Full‑stack spirit: you are comfortable going from AI logic to infrastructure to frontend prototyping when needed. You don't stop at your lane.
• Fast learner: the AI landscape moves fast. You thrive in it. You follow the research, experiment with new models and tools, and you are always slightly ahead of the curve.
• Problem solver: you approach hard technical problems methodically. Latency, cost, hallucinations, long‑term memory — you know these challenges and you enjoy tackling them.
• Team player: you work closely with Product, iterate with users, and communicate clearly about what's working and what isn't.
• Drive & ownership: you take full ownership of your scope. You don't wait to be asked — you spot issues, propose solutions, and ship.
• Language: you are fluent in English (written and spoken).
• Mindset: you have an entrepreneurial mindset, you like challenges, you welcome feedback, and you love constantly learning and getting better.

💎 Our perks

• Flexible remote: if you live in Paris, you can choose to work from our office or from home with no constraints. If you live elsewhere, we can provide access to a coworking space and a coworking budget.
• Work from anywhere: want to spend a month in Italy while working? You can work from most countries in the world for up to 3 months per year.
• Top‑market compensation
• Equity for everyone with the chance to own a piece of what you build
• Half‑day each week dedicated to leveling up with AI by exploring new tools, iterating hard, and sharpening your skills
• Yearly offsite in amazing locations and budget for team‑building events & monthly in‑person gatherings
• Contribution to your ClassPass subscription
• 8‑week leave paid 100% for the second parent
• …and much more, check the full list here!

🤝 Our hiring process

• Intro call: Quick screening with the Hiring Manager or the Talent team.
• Step 1 – Team interview (45 min): Conversation with two Joko team members (could include the Hiring Manager, people from the team you’d join, or colleagues from other teams).
• Step 2 – Role‑specific assessments
  • For non‑tech roles: take‑home case study followed by a 45 min interview. We assess both your output and how you think in real time. The exercise will be relevant to the role (e.g. analysis, strategy, or process design).
  • For tech roles: live technical interviews
    • Coding interview + System design interview
    • For research internships, an additional round may involve analysing and presenting a research paper
• Step 3 – Leadership interview (45 min): Conversation with a SteerCo member and a Founder.
• References: up to 3 calls with former colleagues or managers.

☕ You may also be invited for coffee with team members to get a feel for our culture.