Senior Applied AI Engineer

Operio • Palo Alto, CA

1d • Hybrid

About The Position

Operio.ai is building the next generation of AI-native operational intelligence for fleet and field service organizations. Our platform empowers dispatchers, fleet managers, and field teams with purpose-built AI assistants that turn complex operational data into instant, actionable insight. We are a small, fast-moving team headquartered in Palo Alto—founded by engineers and operators who have built and scaled enterprise software and AI systems.

Requirements

• 4+ years of software engineering experience, with at least 2 years focused on applied machine learning or LLM-based systems
• Demonstrated experience building multi-agent systems using frameworks such as LangGraph, LangChain, AutoGen, CrewAI, or equivalent
• Strong proficiency in Python and production-grade ML/AI engineering practices (testing, observability, CI/CD)
• Hands-on experience with LLM APIs (OpenAI, Anthropic, Gemini, etc.) and retrieval frameworks (vector stores, semantic search, hybrid retrieval)
• Experience with text-to-SQL, structured query generation, or reasoning over relational/semi-structured data
• Track record of delivering AI features in a fast-paced startup or equivalent high-velocity environment
• BS degree or higher in Computer Science, Electrical Engineering, Applied Mathematics, or a closely related technical field

Nice To Haves

• Experience with agentic AI platforms such as Claude Agents, OpenAI Assistants, or similar hosted frameworks
• Familiarity with fleet management, telematics, IoT, or field service operations domains
• Exposure to evaluation frameworks (RAGAS, LangSmith, PromptFlow, custom evals) for LLM quality and regression testing
• Contributions to open-source AI/ML projects or publication of relevant technical work
• Experience working across the full stack in early-stage companies (API design, data pipelines, lightweight front-end integration)
• MS or PhD in a relevant AI/ML field is a plus, but not required

Responsibilities

• Design and implement the Operio multi-agent framework, including agent orchestration, task decomposition, tool use, and memory systems
• Build and optimize LLM-powered pipelines for text-to-SQL, natural language understanding, and structured data reasoning over fleet telemetry and operational data
• Develop retrieval-augmented generation (RAG) and context-reduction strategies to maximize LLM accuracy and cost efficiency at scale
• Architect and maintain prompt engineering systems, evaluation harnesses, and automated testing pipelines for AI features
• Collaborate closely with product and design to translate complex AI capabilities into intuitive user-facing features
• Instrument, monitor, and continuously improve model performance, latency, and reliability in production
• Stay current with the rapidly evolving LLM ecosystem and bring new techniques and tools to the team proactively

Benefits

• Competitive salary and meaningful early-stage equity
• Full medical/dental/vision coverage for employees
• 401k plan
• Generous pre-IPO company equity
• Opportunity to be a defining technical voice at a company building in a rapidly expanding market
• Flexible hybrid work environment in Palo Alto, with autonomy over your tools and workflows

What This Job Offers

• Job Type: Full-time
• Career Level: Senior