Senior AI Engineer

About the job

We are looking for an experienced Senior AI Engineer to drive the development of enterprise AI capabilities across our SaaS platform. Working at the intersection of AI, data, and business domains, you will help transform enterprise knowledge into intelligent, scalable, and production-ready solutions while collaborating closely with engineers, product teams, and domain experts.

Mission

Your mission consists of the following:

• Design and deliver production-grade Agentic AI systems grounded in trusted enterprise knowledge.
• Own the specialist capability for enterprise ontologies and knowledge graphs within Data & AI architecture standards, enabling reliable reasoning, retrieval, and contextual understanding.
• Establish robust AI gateway, evaluation, observability, and governance practices while mentoring engineers and collaborating with domain experts.

Key Responsibilities

Agentic AI Design & Delivery:

• Design and build sophisticated AI agents, orchestrated workflows, multi-agent systems, and LLM-driven reasoning chains.
• Deliver scalable Agentic AI capabilities across SaaS and on-premise applications.
• Balance solution accuracy, latency, security, reliability, and operating cost.

Ontology & Knowledge Graph Ownership:

• Own the lifecycle, architecture, tooling, and quality standards of enterprise ontologies and knowledge graphs within approved enterprise architecture.
• Work with Product Owners and domain experts to model business concepts, relationships, rules, and terminology.
• Maintain semantic consistency, traceability, versioning, and fitness for AI reasoning and discovery.

RAG, Retrieval & Knowledge Integration:

• Design and operate RAG architectures combining vector search, knowledge graphs, and ontology-driven reasoning.
• Define retrieval logic, embedding strategies, context assembly, and grounding quality metrics.
• Partner with Data Engineering, which owns source ingestion, pipelines, lineage, freshness, and source-data quality.

AI Tools, Protocols & Gateway:

• Develop custom tools and MCP servers that securely connect agents to enterprise applications, databases, APIs, and knowledge sources.
• Implement AI gateway capabilities for model routing, fallback, access control, rate limiting, cost monitoring, and multi-model access.
• Build reusable components and interfaces aligned with enterprise engineering standards.

AI Evaluation, Observability & Reliability:

• Implement end-to-end tracing, monitoring, evaluation, and quality controls for LLM and agent workflows.
• Define measurable evaluation methodologies for grounding, task success, safety, latency, and cost.
• Ensure production reliability, security, scalability, compliance, and effective incident diagnosis.

Backend Engineering & Quality:

• Develop robust Python backend services, APIs, asynchronous workflows, and event-driven integrations for AI-powered features.
• Apply clean code, modular design, automated testing, documentation, CI/CD, and containerization practices.
• Conduct code and design reviews and continuously improve performance and maintainability.

Technical Collaboration & Mentoring:

• Translate business requirements into scalable specialist AI solutions.
• Mentor engineers in Agentic AI, knowledge engineering, evaluation, and production practices.
• Collaborate with the Technical Leader, who approves cross-team architecture standards and arbitrates enterprise-wide technical decisions.
• Stay current with relevant AI, LLM, agent, graph, and infrastructure technologies.

Required Experience

• At least seven years of experience in software engineering, AI engineering or a related field.
• At least two years of experience delivering AI/ML or generative AI applications in production.
• Proven experience designing, implementing and maintaining enterprise ontologies and knowledge graphs.
• Strong proficiency in Python and backend API development.
• Experience with FastAPI or similar frameworks.
• Experience with Agentic AI frameworks, RAG, vector search and SQL databases.
• Experience with automated testing and production observability.

Preferred Experience

• Graph databases such as Neo4j.
• Vector-search technologies such as Elasticsearch.
• MCP servers and A2A protocols.
• AI gateways such as LiteLLM.
• LangChain, LangGraph or similar frameworks.
• OpenTelemetry, LangSmith, Langfuse, Arize Phoenix or equivalent tools.
• Docker, Kubernetes or GKE.
• CI/CD and cloud-based SaaS or enterprise applications.
• Experience developing ontologies with business domain experts.

Main Technical Skills

• Python and FastAPI.
• REST APIs, microservices and asynchronous programming.
• Event-driven architectures.
• Agentic AI and multi-agent orchestration.
• LangChain and LangGraph.
• MCP and A2A protocols.
• Enterprise ontology and knowledge graph design.
• Semantic modelling and graph databases.
• RAG, embeddings and vector search.
• Retrieval and LLM evaluation.
• AI gateways, model routing and cost control.
• SQL and Elasticsearch.
• Docker, CI/CD and Git.
• Unit, integration and performance testing.

Behavioral Skills

• Strong technical ownership.
• Structured problem-solving and sound engineering judgement.
• Ability to mentor and share knowledge.
• Effective collaboration with product teams, engineers and domain experts.
• Clear technical and stakeholder communication.

Main Interactions

Internal: AI Software Team, Technical Leader – Data & AI, Data Engineering, Product Management, domain experts, Infrastructure and Security.

External: AI/ML platform vendors, graph technology vendors, cloud service providers and technology partners.

Language and Travel

• Fluent English or minimum B2 level.
• Domestic and occasional international travel may be required.

Location : Belgrade, Serbia

What can you expect from us?

💡Space and encouragement to suggest ideas and solutions

🌍International and multicultural environment

⬆️Interesting internal growth

🤝Soft skill training

💻Internal Academy which is enriched day by day

🧑 Unlimited LinkedIn Learning account

If you recognize yourself in this offer, don't hesitate any longer and send us your application!

How to apply

Applications may be submitted via LinkedIn (please include your CV).

A competitive market salary will be offered to the successful candidate.

About Trace One

Trace One is a premier SaaS provider of Product Lifecycle Management (PLM) and compliance solutions, specializing in the food & beverage, cosmetics, personal care, and chemical industries. With over 30 years of expertise, we empower more than 9,000 brand owners worldwide to innovate, collaborate, and bring products to market faster while ensuring the highest standards of quality, compliance, and sustainability. Trusted by industry leaders, Trace One combines cutting-edge technology with unmatched expertise to help businesses navigate complexity, accelerate growth, and shape a sustainable future.

For more information, visit www.traceone.com

Or follow us on LinkedIn: https://www.linkedin.com/company/trace-one/

and YouTube: https://www.youtube.com/@TraceOne

The Trace One group is an equal opportunities employer.