Hiring: Principal AI Engineer Company: Obin AI Location: New York, United States Job Posted Time: 2026-09-12 17:57:41 Employment Type: Full-time Target Skills & Keywords: Agentic AI, Multi-Agent Systems, LLM-Powered Agents, RAG, Python, GCP, AI/ML Frameworks, Agent Orchestration, AI Safety & Evaluation, Production Infrastructure, APIs, System Architecture Experience: - 10–15+ years of software engineering experience - 5–8+ years of hands-on experience building AI/ML systems/frameworks, LLM-based agents, and/or RAG systems in production - Experience logging, evaluating, and optimizing AI applications Required Skills: - Designing and deploying LLM-powered agents using prompt design, tool use, orchestration logic, and system evaluation - Expertise in agent-to-agent (A2A) orchestration protocols, self-correcting agent loops, and prompt-routing middleware - Proficiency in Python and modern AI/ML frameworks - Cloud infrastructure experience (GCP preferred) and APIs - Architecting and maintaining backend systems and APIs with high availability, performance, and observability - Balancing accuracy, latency, reliability, cost, and explainability in agentic systems - Strong intuition around system architecture, performance, and scaling - Clear communication in ambiguous, high-stakes problem spaces Qualifications: - Recognized technical authority in multi-agent systems; publishes reusable blueprints/reference architectures - Sets architecture for agentic AI systems across products; solves ambiguous problems inherent to non-deterministic systems (context pollution, runtime state handoffs, safety) - Drives AI safety/reliability practices and evaluation standards; mentors senior engineers - Owns agentic AI strategy across the product suite; sets governance standards for agent evaluation, safety, and autonomy - Represents the company externally (conferences, open source, technical publications) - Partners with technical and non-technical stakeholders at major credit firms to co-develop AI solutions tied to ROI - Helps define engineering culture, hiring bar, and long-term technical roadmap - Hunger to move fast, own outcomes, and build something enduring Bonus: - Experience with human-in-the-loop systems, feedback loops, and long-horizon agentic task execution - Background in financial systems, risk modeling, or decision automation - Familiarity with PydanticAI, LlamaIndex, Google ADK, Claude Agent SDK, or similar frameworks - Built or contributed to an internal AI platform or reusable LLM tooling Compensation: Not specified Interested candidates, please apply directly through the job posting on company's career page or try via AI auto apply on this platform. Don’t miss this opportunity to join a forward-thinking team!