Principal AI Engineer
Summary
Early engineering hire at Obin, a startup building LLM-powered multi-agent systems to automate credit workflows. The engineer designs agentic AI architectures (LLM, RAG, orchestration), owns production backend/API infrastructure, evaluates and optimizes for accuracy, latency, cost and safety, and works directly with credit-firm customers. Core stack: Python, LLM/agent frameworks, GCP, APIs.
- Recognized technical authority in multi-agent systems; publishes reusable blueprints/reference architectures; represents the company externally (conferences, open source, technical publications).
- Designing and Deploying LLM-Powered Agents
- 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
- Logging, evaluating, optimizing AI applications
- Sets architecture for agentic AI systems across products; solves ambiguous problems inherent to non-deterministic systems (context pollution, runtime state handoffs, safety).
- Expert in agent-to-agent (A2A) orchestration protocols, self-correcting agent loops, prompt-routing middleware; drives AI safety/reliability practices and evaluation standards; mentors senior engineers.
- Proficiency in Python and experience with modern AI/ML frameworks and cloud infrastructure (GCP preferred)
- Experience with cloud infra (preferably GCP) and APIs
- Hunger to move fast, own outcomes, and build something enduring
- Strong intuition around system architecture, performance, and scaling
- Clear communication, especially in ambiguous, high-stakes problem spaces