About the Role
We are looking for an experienced AI Engineer or AI Architect to lead the design and deployment of AI-powered systems for Olverin Ventures and our clients. This is a senior technical leadership role at the frontier of what we build — you will be responsible for defining our AI architecture standards, selecting and integrating models, building production AI agents and automation pipelines, and keeping our AI capability at the leading edge of the field.
This role suits a practitioner who has moved beyond AI experimentation into production AI system engineering — someone who has deployed AI agents, RAG systems, or LLM-integrated applications into real business environments and understands the difference between a working prototype and a production-ready system.
What You Will Do
- Design and implement custom AI agents for client use cases including customer service, sales qualification, operations automation, research, and data processing
- Architect RAG (Retrieval-Augmented Generation) systems, fine-tuning pipelines, and multi-agent orchestration frameworks
- Integrate LLMs (OpenAI, Anthropic, open-source models) into business applications via API and custom middleware
- Build AI-powered content generation workflows with appropriate human-in-the-loop quality control
- Implement AI-driven security monitoring and anomaly detection systems
- Evaluate new AI models, frameworks, and platforms and make adoption recommendations
- Define AI system architecture standards, prompt engineering best practices, and evaluation frameworks for the team
- Collaborate with the engineering team on integrating AI components into broader product architecture
- Communicate AI capabilities, limitations, and recommendations clearly to non-technical clients and stakeholders
What We Are Looking For
- 3+ years of professional AI/ML engineering experience with a focus on LLM-based systems
- Demonstrable production deployments of AI agents or LLM-integrated applications
- Strong Python skills — you build production-quality code, not just notebooks
- Deep familiarity with LangChain, LlamaIndex, or equivalent orchestration frameworks
- Experience with vector databases (Pinecone, Weaviate, Qdrant, or similar) for RAG implementations
- Proficiency with the OpenAI and/or Anthropic APIs including function/tool calling, streaming, and context management
- Understanding of AI evaluation methodology — you measure system performance systematically, not anecdotally
- Production deployment experience — Docker, cloud platforms, API design, monitoring, and observability
- Strong written communication — you document systems thoroughly and explain technical concepts clearly
Nice to Have
- Experience with open-source models and local deployment (Ollama, vLLM, or similar)
- Fine-tuning experience with LoRA, RLHF, or equivalent techniques
- Background in NLP, information retrieval, or machine learning research
- Familiarity with AI cybersecurity applications — anomaly detection, behavioral analysis, threat classification
- Experience integrating AI into eCommerce, CRM, or marketing automation systems
- Contributions to open-source AI projects or published writing on AI engineering
How to Apply
Send your CV, links to any relevant projects, GitHub profile, or writing about AI systems, and a brief description of the most technically complex AI system you have built and deployed
