Senior AI Engineer

Roboyo is a category shaper in Agentic Automation. We help leading brands embed autonomous, AI‑powered agents into their workflows, processes, products and services so they can scale faster and operate smarter.

Built on a strong automation heritage, we focus on seamless integration of AI into enterprise level organization, not just proving concepts, but owning outcomes and driving value in every industry we are present. At Roboyo, you’ll join a global team of builders, consultants and engineers that are top practitioners of taking solutions to the next level for clients in pursuit of excellence.

 

About the Role 

We are seeking a highly experienced Senior AI Engineer to join our team supporting our enterprise clients. In this role, you will design, develop, and maintain enterprise-grade AI solutions built on cutting-edge LLM platforms, conversational AI frameworks, and cloud-based data ecosystems. You will be a key contributor to AI-powered product development and work closely with cross-functional stakeholders to deliver impactful, scalable solutions. 

Key Responsibilities 

AI Platform Development & Integration 

• Architect, deploy, and manage AI-powered conversational platforms using LibreChat as the primary open-source framework. 

• Integrate and configure multiple LLM providers including Google Gemini, OpenAI, and other foundation models within enterprise environments. 

• Build and maintain AI pipelines including retrieval-augmented generation (RAG), prompt chaining, and agentic workflows. 

• Design and implement O365 Connectors to enable seamless AI integration with Microsoft Teams, Outlook, SharePoint, and related enterprise tools. 

• Build a scalable platform leveraging MongoDB, Vector DB and K8S/GKE clusters 

LLM Orchestration & Customization 

• Develop and fine-tune prompt engineering strategies, system instructions, and tool/function calling configurations across different LLM providers. 

• Build multi-agent workflows using frameworks such as LangChain, LlamaIndex, AutoGen, or similar orchestration libraries. 

• Evaluate model performance, hallucination rates, and benchmark LLMs for domain-specific use cases within the hospitality and gaming industry. 

System Architecture & DevOps 

• Design secure, scalable AI architecture aligned with enterprise security policies and compliance requirements. 

• Containerize and deploy AI services using Docker and Kubernetes; manage CI/CD pipelines for model serving and application delivery. 

• Implement monitoring, observability, and logging for AI systems in production environments. 

Collaboration & Stakeholder Management 

• Work closely with business analysts, product owners, and client stakeholders to translate requirements into technical solutions. 

• Produce and maintain comprehensive technical documentation including architecture diagrams, API specs, and runbooks. 

• Mentor junior engineers and conduct code reviews; champion best practices in AI engineering across the team. 

Required Skills & Technical Expertise 

LibreChat	MongoDB	LangChain / LlamaIndex
Google Gemini	O365 Connectors	REST APIs
RAG Architecture	Python	PostgreSQL
Docker / Kubernetes / GKE	pgvector / Vector DB	Google Cloud Runner

 

Must-Have Skills 

• LibreChat Platform – Hands-on experience deploying, customizing, and administering LibreChat for enterprise use; familiarity with LibreChat configuration, plugin/tool integrations, and multi-provider LLM setup. 

• Vector Databases – Practical experience implementing vector search using pgvector on PostgreSQL; understanding of embedding models, dimensionality, and retrieval strategies for RAG use cases 

• Microsoft 365 Integration – Experience building O365 connectors and integrations with Microsoft Teams, Outlook, and SharePoint; familiarity with Microsoft Graph API and Adaptive Cards.O365 Connectors:  

• LLM Integrations – Experience integrating Google Gemini (via Vertex AI or API), OpenAI, and other foundation models; understanding of model versioning, token management, cost optimization, and safety guardrails. 

Good-to-Have Skills 

• Experience with other Vector DB platforms such as Pinecone, Weaviate, Qdrant, or Chroma. 

• Exposure to RPA tools or workflow automation platforms that complement AI pipelines. 

• Knowledge of hospitality or gaming domain  

• Experience with AI governance, responsible AI practices, and content safety frameworks. 

Qualifications & Education 

• Bachelor's or Master's degree in Computer Science, Engineering, Artificial Intelligence, or a related technical discipline. 

• 6–10 years of overall IT experience with at least 5+ years in AI/ML engineering, NLP, or LLM-focused development. 

• Strong command of Python; secondary proficiency in JavaScript/TypeScript is preferred. 

• Demonstrated track record of delivering enterprise AI solutions in production environments. 

• Excellent communication skills with the ability to present technical concepts to non-technical stakeholders. 

We are an equal opportunity employer and value diversity at our company. We do not discriminate on the basis of race, religion, color, national origin, gender, sexual orientation, age, marital status, veteran status, or disability status.

Privacy Notice: By applying, you consent to the processing of your personal data for recruitment purposes in line with our Privacy Policy: https://roboyo.global/data-privacy/