OOLIO
Website:
oolio.com
Job details:
ABOUT OOLIO:
Oolio is a leading B2B SaaS platform transforming how hospitality venues operate and grow. Trusted by more than 22,000 venues, we power mission-critical POS, payments, online ordering, kiosks, loyalty, kitchen management, and real-time insights — all within one connected ecosystem.
We are building the operating system for modern hospitality — simplifying complex operations, accelerating service, and unlocking smarter, data-driven decisions. Built by hospitality professionals with decades of industry experience, we understand the realities of every shift, every service rush, and every guest interaction. From cafés and quick-service restaurants to pubs, multi-site groups, and stadiums, Oolio enables venues to operate seamlessly at scale. With next-business-day settlements, powerful third-party integrations, and 24/7 real human support, we go beyond software — we become long-term partners in growth.
As a rapidly scaling product-led organisation, we’re shaping the future of hospitality technology.
We build the technology backbone that powers modern hospitality businesses to perform, compete, and thrive at scale.
JOB DESCRIPTION:
At Oolio, Senior AI Engineers are AI-native product builders who design and operate autonomous systems that power next-generation B2B SaaS platforms. You will move beyond traditional coding to build systems where agents execute, validate, and evolve software with minimal human intervention.
You will collaborate closely with Product, Design, and Engineering teams to translate business intent into self-operating, scalable AI systems built for reliability, performance, and continuous learning.
RESPONSIBILITIES:
- Own end-to-end development of AI-native systems—from architecture and orchestration design to deployment, observability, and production reliability.
- Design and build autonomous multi-agent systems that follow intent → execution → validation → refinement loops.
- Develop long-running agent-based development harnesses capable of navigating codebases, implementing features, generating tests, and raising production-ready PRs.
- Architect and implement context engineering systems including retrieval pipelines, memory layers, and grounding strategies to ensure low hallucination and high accuracy.
- Design and orchestrate multi-agent workflows (Planner → Executor → Validator → Reviewer) with strong control over state, communication, and determinism.
- Build and optimize RAG systems over codebases, enabling agents to reason over large-scale repositories, logs, schemas, and documentation.
- Develop reusable AI skills, tools, and plugins to enable agents to operate across codebases, CI/CD pipelines, observability systems, and production environments.
- Implement AI-driven testing and validation pipelines, including automated test generation, execution, and continuous validation loops integrated into CI/CD.
- Build AI-powered systems for on-call automation and incident triage, capable of analysing logs, metrics, and traces to identify root causes and trigger remediation.
- Ensure robustness through safe retries, fallback strategies, and fault-tolerant agent design.
- Optimize system performance, latency, and reliability for large-scale AI-driven workflows.
- Drive observability best practices including structured logging, monitoring, tracing, and feedback loops for AI systems.
- Participate in design reviews and actively contribute to evolving AI engineering standards and best practices.
- Troubleshoot complex production issues in autonomous systems, perform root cause analysis, and implement long-term systemic improvements.
- Collaborate with cross-functional teams to build scalable, secure, and intelligent product experiences.
REQUIREMENTS:
Role: Senior AI Engineer - final role will depend on candidate credentials and interview outcomes
Experience: 3 – 8 Years (strong hands-on engineering + AI systems experience)
Education: Preferred – M.Sc/B.Tech/B.E/M.Tech/M.E/MCA/M.S
Technology Stack:
- Core Engineering: Distributed Systems, APIs, Microservices
- LLM & AI Ecosystems: OpenAI, Anthropic, or open-source models (LLaMA, Mistral, etc.)
- Agent Frameworks & Runtimes: LangChain, LangGraph, AutoGen, OpenHands, or similar
- RAG & Retrieval Infrastructure: Vector databases (Pinecone, Weaviate, FAISS), embeddings pipelines, retrieval optimization
- Context & Memory Systems: Redis, graph-based memory, or custom state management architectures
- AI Observability & Evaluation: Langfuse, Helicone, prompt/response tracing, evaluation frameworks, guardrails
- Cloud & Infrastructure: AWS (preferred), Kubernetes, Docker, CI/CD pipelines
Other Requirements:
- Strong experience building production-grade backend or distributed systems in product-based organisations
- Hands-on experience with AI-native development workflows and agent-based systems
- Deep expertise in context engineering (RAG, memory, grounding) and multi-agent orchestration
- Proven experience building autonomous development harnesses and AI-driven testing/validation systems
- Strong understanding of stateful agent systems, memory management, and execution models (deterministic vs probabilistic)
- Solid grasp of fault tolerance, retries, and fallback strategies in autonomous systems
- Demonstrated ability to move beyond prompt chaining to stateful, multi-step agent systems with memory and evaluation loops
- Proven track record improving hallucination control, retrieval quality, and overall system reliability in production
- Experience integrating AI systems with code repositories, CI/CD pipelines, observability platforms, and live production environments
- Familiarity with OpenHands, Conductor, Claude Code, or similar agent-based tools
- Strong inclination toward first-principles system design over tool-specific approaches
- Excellent problem-solving skills in high-complexity, evolving AI systems
- Experience working in high-scale or high-impact environments is a plus
Click on Apply to know more.