Solution Architect - Agentic Solutions (Zurich)
We invite you to apply for the Solution Architect - Agentic Solutions (Zurich) role at Iris.ai, an AI-first company dedicated to transforming how humans discover and apply knowledge. For over a decade, we’ve built intelligent systems that empower researchers, engineers, and product teams to work faster and more precisely with scientific and technical data.
Our product suite—Neuralith, Axion, and RSpace—supports end-to-end AI development, from data orchestration and retrieval to LLM evaluation and deployment. At the core of our work are Retrieval-Augmented Generation (RAG) pipelines, LLM evaluation frameworks, and intelligent AI agents that bring context-awareness, accuracy, and task-level reasoning to applied AI.
Backed by the European Innovation Council (EIC) and trusted by leading R&D teams across industries, we turn advanced AI research into real-world tools that help organizations solve high-impact problems.
Overview
As a Solution Architect at Iris.ai, you’ll join a remote-first, AI‑native team focused on building production-ready systems powered by RAG, LLMs, and AI agents. You will play a pivotal role in shaping next-generation AI agents that bring context-awareness, accuracy, and complex reasoning to real-world problems. You will work alongside our commercial, product, and development teams to design, prototype, and deploy intelligent systems—leveraging our Neuralith, Axion, and RSpace products.
Technologies Used In The Job Include
Rapid prototyping tools (AI‑Assisted Coding – Windsurf, Cursor, Flowise, Lovable, etc.)
Cloud & Infrastructure (AWS, GCP, Azure, Kubernetes, Docker, Terraform)
Retrieval‑Augmented Generation (RAG) pipelines (ChromaDB, SentenceEmbeddings, LLMs)
AI Agent frameworks (Autogen)
Machine Learning stacks (PyTorch, TensorFlow, etc.)
Backend & APIs (Python, Django, etc.)
Git & CI / CD
What You’ll Do
Design end‑to‑end Agentic solutions based on Iris.ai’s products for enterprise clients: build modular pipelines that combine data ingestion, RAG, LLM evaluation, and autonomous decision‑making into cohesive workflows that deliver direct value.
Rapid prototyping – spin up proof‑of‑concepts, run benchmarks on accuracy and reasoning performance, and iterate based on real‑world data with the client.
Integration and deployment – collaborate with the tech team to deliver, orchestrate, and monitor AI agents in production environments.
Engage in sessions with the client – translate customer requirements into technical designs, run technical sessions, and provide best‑practice guidance for AI adoption.
Collaborate in a cross‑functional team – work closely with sales managers, product managers, engineers, designers, and researchers to align architecture with product vision and user needs.
Drive innovation – test new approaches with clients and bring new ideas to the product team.
Ensure client systems are scalable, testable, and maintainable, focusing on performance and reliability.
Thrive in a remote‑first, agile environment, contributing meaningfully within a distributed, deep‑tech team.
Keep learning, always – we’ll support you with mentorship and resources to grow as an AI engineer.
What You Need
5+ years in client‑facing, product‑oriented roles—ideally in AI/ML or data‑driven platforms.
Deep understanding of LLMs & RAG, with 1+ year hands‑on experience in prompt engineering, retrieval pipelines, and evaluation metrics.
Strong software engineering skills: proficient in Python, API design, and microservices.
Cloud proficiency: designing and operating scalable services on AWS, GCP, or Azure.
Solid experience in web development (Django, Flask, REST).
Excellent communication—able to convey complex technical concepts to both technical and non‑technical stakeholders.
Problem‑solver mindset: keen analytical skills, resourcefulness, and a drive to tackle ambiguous challenges.
Ability to work in a remote‑first, collaborative environment.
Proficiency in English.
Any Of These Is An Advantage
Advanced degree in Computer Science or related field.
Previous work with LLMs, NLP, or AI model evaluation.
Certification in cloud computing.
Previous experience deploying RAG solutions in scalable production environments.
Open‑source contributions, academic research, or mentoring.
Life At Iris Offers
Build responsible AI that shapes the future of science and tech.
Join a sharp, versatile team of ambitious builders.
Thrive in a flat structure with no corporate hierarchy, where every voice matters.
Compensation
Competitive salary with annual reviews.
Stock options to share in our long‑term success.
Work Your Way
30 days annual paid vacation + bonus days.
Flexible work hours.
Flexible work location—choose where you work from.
Hybrid model or 100% remote work—your preference.
Regular team‑building activities and travels.
Seasonal working camps (summer / winter).
Personalized work equipment allowance—choose your gear.
Grow With Us
Learning & development allowance—sponsored conferences and upskilling courses.
Career enhancement plan.
New technologies introduction and testing opportunities.
Knowledge transfer, work buddies, pair coding, mentorship opportunities, weekly tech deep dives.
Workshops, conferences, hackathons.
Freedom to bring innovation and your ideas to life.
Wellbeing & Perks
Free MultiSport card.
Cool Sofia office in a central location.
Private health insurance—premium package.
Bi‑annual health checks.
Charity and volunteer activities.
Seniority Level
Mid‑Senior level
Employment Type
Full‑time
Job Function
Engineering and Information Technology
Industries
Software Development
#J-18808-Ljbffr