The GenAI Architect will implement AI solutions, evaluate existing systems, and collaborate on AI strategies, ensuring alignment with business objectives.
The company and our mission:
Zartis is a digital solutions provider working across technology strategy, software engineering and product development.
We partner with firms across financial services, MedTech, media, logistics technology, renewable energy, EdTech, e-commerce, and more. Our engineering hubs in EMEA and LATAM are full of talented professionals delivering business success and digital improvement across application development, software architecture, CI/CD, business intelligence, QA automation, and new technology integrations. At Zartis, we are committed to building an inclusive culture based on trust and innovation.
We are looking for a GenAI Architect who plays a critical role in the successful implementation of AI solutions within the organization.
The project:
You will be working across different AI projects within Zartis alongside talented teammates from a variety of backgrounds. You will be part of a distributed team developing new technologies to solve real business problems. As part of this role, your primary areas of expertise must include:
Auditing Existing Products: The GenAI Architect will evaluate current systems and processes to identify areas where GenAI could bring about improvements or solve problems. This involves understanding the business needs, assessing the suitability of existing data and technology infrastructure, and suggesting theoretical AI solutions. In this role, the GenAI Architect should be up to date with all the most relevant technological and academic developments in LLMs and agentic AI.
Implementing GenAI Solutions: The GenAI Architect will be responsible for the practical application of GenAI solutions. This includes designing and implementing LLM-based applications, integrating them into existing products or services, and ensuring they function as expected. The AI Architect will work closely with data scientists, engineers, architects and product teams to ensure the AI solutions meet the business objectives.
Collaborating on AI Strategy: This will involve working closely with stakeholders to align AI initiatives with overall business goals, analyzing the impact of deployed GenAI solutions through metrics and KPIs, and leveraging insights from these evaluations to refine and adjust the AI strategy accordingly. By continuously integrating feedback and learnings from ongoing projects, the GenAI Architect will ensure that the AI strategy remains dynamic, responsive to business needs, and capable of seizing new opportunities for innovation and improvement. This strategic collaboration guarantees that AI deployments not only address current challenges but also set the foundation for future advancements.
What you will bring:
- Demonstrated ability to take a GenAI application from ideation through design, prototyping, production deployment, monitoring, and iteration.
- Combined expertise in LLM engineering, RAG design, and agentic orchestration with production-grade software engineering and DevOps skills.
- Hands-on experience developing multimodal and Agentic RAG pipelines that involve parsing and retrieving from diverse data types (text, images, charts, documents).
- Knowledge of integrating vector databases, metadata filters, and graph-based memory structures to support complex reasoning.
- Ability to design and deploy agentic systems using industry-standard frameworks while abstracting tools effectively (tool schemas, action layers, etc.).
- Understanding when to apply orchestration strategies (e.g. ReAct vs. planner-executor) depending on use case requirements.
- Familiarity with wiring up tools like LangSmith, latency/factuality metrics, and automated A/B testing in real-world pipelines.
- Scalable and Cost-Conscious Engineering
-Experience balancing performance, scalability, and cost in LLMOps, including: token budgeting, usage quotas, and observability tools for tracing and optimization.
- Ability to manage the trade-offs between classic NLP approaches and large-model heuristics when required by efficiency goals.
- Very strong communication and collaboration skills.
Nice to have:
- Knowledge of Classic NLP techniques (NER, parsing, tf-idf, etc.) to complement LLM heuristics when lighter, cheaper, faster or better would be a great addition to your skillset.
- Ability to use ML models (re-rankers, regressions, embeddings, etc.) that boost overall LLM application quality.
- Graph theory and Graph Data Science: Custom graph-based retrieval or memory stores for agents; supports richer reasoning paths.
What we offer:
- 100% Remote Work
- WFH allowance: Monthly payment as financial support for remote working.
- Career Growth: We have established a career development program accessible for all employees with a 360º feedback that will help us to guide you in your career progression.
- Training: For Tech training at Zartis, you have time allocated during the week at your disposal. You can request from a variety of options, such as online courses (from Pluralsight and Educative.io, for example), English classes, books, conferences, and events.
- Mentoring Program: You can become a mentor in Zartis or you can receive mentorship, or both.
- Zartis Wellbeing Hub (Kara Connect): A platform that provides sessions with a range of specialists, including mental health professionals, nutritionists, physiotherapists, fitness coaches, and webinars with such professionals as well.
- Multicultural working environment: We organize tech events, webinars, parties, and activities to do online team-building games and contests.
