Senior AI Engineer

We are looking for a visionary Senior AI Engineer who will bridge the gap between high-level architecture and hands-on execution, specifically focusing on simplifying enterprise integration for AI agents. As a key hire during our current growth phase, you will define the standards for how our platform scales and interacts with other enterprise applications.

What You’ll Do

• Design and implement multi-agent systems and orchestration layers.
• Build and operate observability stacks (e.g., OpenTelemetry) to monitor agent reasoning paths, tool usage, and performance in real-time.
• Develop and enforce technical safety mechanisms—such as input/output filtering and behavioral boundaries—to mitigate risks like hallucinations, prompt injections, and bias.
• Analyze telemetry and execution traces to create feedback loops for continuous agent improvement and automated evaluation.
• Securely connect agents to external services, unstructured data, and enterprise APIs via robust tool-calling schemas.
• Implement fallback mechanisms, human-in-the-loop (HITL) checkpoints, and automated recovery for agentic failures.
• Implement best practices for MLOps, monitoring, and performance tuning of AI models in live environments
• Automate SDLC processes and CI/CD pipelines, elevate QA standards, and develop incident response protocols to enable high velocity, availability and reliability of our platform

Who You Are

• You thrive in the "ambiguity phase" of a startup but build with the discipline of an enterprise-grade engineer.
• You are a "force multiplier" who elevates the technical bar for the entire team.
• You are obsessed with the practical application of AI, moving beyond demos to create reliable, production-hardened products
• You have a high-confidence, low-ego mindset

What We’re Looking For

• 7 + years of senior engineering experience at a fast-paced, high-growth technology startup that has successfully scaled from early stage through Series A/B funding (or equivalent growth phase)
• 2+ years of ML, including experience focused on LLMs or agentic workflows.
• Proficiency in agent orchestration and memory-augmented systems.
• Hands-on experience analyzing tracing and logging data.
• Experience using feedback loops to continuously improve ML systems
• Built agents that invoked tools or utilized Model Context Protocol (MCP) to access enterprise data sources
• Proficiency in modern technologies (e.g., Python, semantic search, vector DBs, GraphQL, queues, containers, Kubernetes, real-time data processing, Spark, Open Telemetry, Clickhouse)
• Thrives in startup ambiguity while maintaining the discipline of an enterprise-grade engineer
• Acts as a force multiplier who elevates the technical bar for the entire team
• Obsessed with practical application of AI systems and capable of building enterprise solutions that solve real-world customer problems

What We Offer

• Remote workplace with occasional in-person onsite meetings in SF Bay Area
• Generous equity grants of ISO stock options
• Exceptional benefits package for health, dental, vision, and life insurance