Senior AI Engineer

Svitla Systems Inc. is looking for a Senior AI Engineer for a full-time position (40 hours per week) in Europe. Our client is a leading expert network that provides business and government professionals with opportunities to communicate with industry and subject-matter experts to answer research questions. Customers consult with these experts over the phone and in person at conferences, teleconferences, custom events, and workshops. Their multinational customer list includes nine top 10 consulting firms, hundreds of hedge funds, and many of the largest private equity firms and Fortune-ranked companies.  

We are seeking a Senior AI Engineer with hands-on experience in production-grade LLM systems, well beyond MVPs or proof-of-concept prototypes. The ideal candidate will possess a deep understanding of modern AI infrastructure and LLM Ops, and extensive experience deploying and maintaining LLM-powered applications at scale in enterprise environments. It is a strategic, high-impact role for a technically strong, innovation-driven engineer who thrives on solving complex challenges in the generative AI space. 

Requirements:

• 2+ years of experience working with LLM providers (OpenAI, Anthropic, Google Gemini), implementing RAG, hybrid search, and multi-agent architectures.

• Hands-on experience with agentic AI systems and relevant system design. GenAI experience (Agents, LLMs, RAG, etc ) and Backend Engineering (APIs/Microservices, Deployment, Data Engineering, etc).

• Demonstrated success delivering LLM-based systems in production environments (not limited to MVP or PoC).

• Strong understanding of retrieval-augmented generation, vector databases, and prompt engineering.

• Hands-on experience with LangChain, LlamaIndex, Pinecone, or equivalent frameworks.

• Practical experience implementing LLMOps, AI observability, and hallucination mitigation strategies.

• Experience creating or integrating AI agents within enterprise systems.

• Deep knowledge of Python, backend frameworks (FastAPI, Flask), and asynchronous programming.

• Experience with Docker, Kubernetes (AKS preferred), Helm, and cloud environments (Azure, AWS, or GCP).

• Familiarity with Databricks, Apache Spark, and large-scale data processing pipelines.

• Experience with LLM evaluation, MLflow, and performance/drift monitoring.

• Ability to mentor engineers and lead complex, distributed AI system builds.

Nice to have:

• Experience with large-scale data integration and model deployment pipelines.

• Familiarity with AI safety, governance, and compliance frameworks.

• Exposure to enterprise AI adoption strategies and cross-functional collaboration.

  
  

Responsibilities:

• Design, build, and operate scalable, low-latency backend services and APIs powering Generative AI features — from retrieval-augmented generation (RAG) pipelines to multi-agent systems.

• Oversee the full lifecycle of AI-powered applications, including system design, development, CI/CD deployment, monitoring, and optimization in production environments such as Databricks and Azure Kubernetes Service (AKS).

• Continuously refine retrieval and generation performance using advanced retrieval optimization, re-ranking, chunking strategies, and prompt engineering for hallucination reduction.

• Develop solutions that combine LLMs with proprietary knowledge bases, external APIs, and real-time data streams, enabling sophisticated copilots and research assistants.

• Collaborate with AI and engineering teams to establish LLMOps best practices—including automated evaluation (LLM Judges, MLflow), AI observability, and system monitoring.

• Experiment with advanced prompting and interaction methods (e.g., Chain-of-Thought, ReAct) to enhance LLM performance, accuracy, and safety.

• Provide technical mentorship and leadership through code reviews, design discussions, and cross-functional collaboration to elevate overall engineering standards.

• Partner with product and business stakeholders to define AI priorities, translate user needs into technical requirements, and shape the evolution of AI offerings.

We offer:

• US and EU projects based on advanced technologies.

• Competitive compensation based on skills and experience.

• Regular performance appraisals to support your growth.

• Flexibility in workspace, either remote or our welcoming office.

• Bonuses for article writing, public talks, and other activities.

• Generous time off, including vacation, national holidays, sick leaves, and family days.

• Personalized learning programs tailored to your interests and skill development.

• Free tech webinars and meetups organized by Svitla.

• Regular corporate online activities.

• Awesome team and a friendly, supportive community!