AI Solution Architect

What is the project, and why should you care?

Symphony Solutions is a Cloud- and AI-driven IT company headquartered in the Netherlands. We deliver tailored software solutions across Healthcare, Wellbeing, Airline, and other industries. Since 2008, we’ve been providing full-cycle software development, data and analytics, cloud engineering, ML & data engineering service, full-cycle development of AI solutions, and digital marketing orchestration for clients across Western Europe and North America.

Our solution is one of Symphony’s most innovative projects — an AI-powered personal intelligence platform that acts as a digital twin and “second brain.” It combines Voice services, multi-agents, external memory architecture, and LLM fine-tuning to simplify complex digital interactions and provide personalized insights for users.

As the AI Solution Architect, you’ll play a pivotal role in designing the platform’s technical and AI foundations, ensuring its security, scalability, reliability, and intelligence.

You will be an excellent fit for this position if you have:

Core Experience:

• 7+ years of experience in software development (Python, Kotlin, Java, or C#), including 2+ years in solution or AI architecture.
• Proven track record in AI/ML system design, integrating speech recognition (Speech to Text, Text to Speech, Speech to Speech), NLP, and contextual search, development of Gen-AI-based solutions, including RAG, LLM fine-tuning, and real-time speech handling.
• Experience leading cross-functional teams (AI, data, mobile, and backend engineers).
• Deep understanding of mobile and cloud integration patterns.
• Familiarity with Agile/Lean delivery and startup-like MVP development environments.

Architecture & Cloud Proficiency

• Expertise in GCP (Vertex AI, Cloud Run, Firestore, BigQuery ML, Serverless, Firebase and Postgres); AWS and Azure also acceptable.
• Strong grasp of microservice, event-driven, and serverless architectures.
• CI/CD, containerization, and observability experience (GitHub Actions, Kubernetes, Docker, Prometheus, Grafana), experience working with vector and graph databases.
• Experience implementing privacy-first AI architectures (GDPR-compliant data storage, anonymization, zero-knowledge).

AI & GenAI Expertise

• Practical understanding of LLMs, LLM fine-tuning, RAG, multi-modality, Agentic AI, and Multi-agent architecture.
• Hands-on experience with LangChain, LlamaIndex, or AutoGen for model orchestration.
• Knowledge of vector databases (Pinecone, Qdrant, Weaviate) and contextual memory design.
• Familiarity with speech-to-text and TTS models (Whisper, Azure Cognitive Services, ElevenLabs).
• Understanding of prompt engineering, meta prompting, and evaluation frameworks (TruLens, Vertex Evals).
• Awareness of AI trust, explainability, and bias mitigation practices.

Data Systems & Engineering

• Experience with data ingestion and transformation pipelines (Airflow, Kafka, Spark).
• Familiarity with embedding-based search systems and knowledge graph structures.
• Understanding of semantic memory models for personal assistant applications.

Soft Skills

• Excellent stakeholder communication and technical storytelling.
• Consulting mindset — ability to shape technical vision based on evolving business goals.
• Capable of leading AI discovery workshops, technical PoCs, and pre-sales solution design.
• Collaborative leadership, inspiring innovation and ownership across the team.

Preferred Qualifications

• Master’s degree in Computer Science, AI, or Data Engineering.
• Nice to have certifications: AWS ML Specialty, Google ML Engineer, or Cloud Architect (any platform).
• Previous experience designing AI-first consumer or voice-based applications.
• Strong understanding of AI governance, trust, and responsible AI principles.
• Proven delivery record in AI companion or context-aware assistant projects.

Here are some of the things you’ll be working on:

Mission

• Define and drive the AI architecture and technical direction for the platform.
• Transform business goals (e.g., digital twin, second brain, contextual AI) into scalable and production-ready solutions.
• Collaborate with Product Owner, Delivery Manager, and AI engineers to align strategy, feasibility, and innovation.

Key Responsibilities

• Architect end-to-end architecture and design of the application, including its components: mobile apps, real-time voice handling, AI agents, and cloud infra services.
• Design agentic orchestration pipelines that allow autonomous collaboration between AI agents.
• Oversee the integration of LLMs, embeddings, vectors, networks, and other databases into the core memory framework.
• Define data privacy and ethical AI guidelines for the product.
• Support PoC and MVP phases, validating approaches for multimodal (voice/text) interactions.
• Mentor engineering teams in AI-first architecture and MLOps/LLMOps best practices.
• Lead technical feasibility assessments and manage trade-offs between innovation and scalability.
• Collaborate on AI roadmap evolution toward a fully personalized, on-device digital twin.

Expected Results

• Deliver a robust AI architecture blueprint.
• Co-led the Agentic Orchestration Layer design and deployment for internal and production use.
• Implement end-to-end LLM evaluation & monitoring within 6 months of MVP launch.
• Enable continuous learning and improvement loops across AI components (speech, memory, reasoning).