Principal Engineer (AI Fluent)
On-siteHerzliya, Tel Aviv, Israel
Herzliya, Tel Aviv, IsraelOn-siteFull TimeSenior LevelFintech ServicesLarge
Full TimeSenior LevelLargeFintech Services
Job Summary
Own the full loop from problem definition through production delivery, architecting AI solutions without hand-held specs. Build with AI as your primary tool to accelerate delivery, co-design decision logic with stakeholders, and construct evaluation harnesses before shipping. Manage production support and monitoring for systems handling real money, maintaining reliability, security, and cost awareness. Report to a Domain Architect while working directly with senior engineering and business leaders on high-impact challenges.
Required Qualifications
- 7Y+ of Experience shipping production AI systems
- Understanding of agentic architectures
- Strong eval instincts
- Full-stack range
- Comfortable across any stack
- Honest communication
- Understanding of production concerns such as reliability, maintainability, security, observability, latency, and cost
- Real fluency with AI coding tools
- Think in workflows, not endpoints
- Clear judgment about when to trust AI output and when to rewrite it
- Goes beyond using AI - builds skills, workflows, and harnesses, not just prompts
- Understanding of common AI-system risks such as hallucinations, prompt injection, data leakage, unreliable tool execution, and uncontrolled autonomy
- 7Y+ of Experience shipping production AI systems - running them in the real world and fixing what breaks, not just building them
- Understanding of agentic architectures - orchestration, multi-step workflows, fallback and error logic
- Strong eval instincts - you define metrics, build test sets, and don't ship until you can measure
- Full-stack range - comfortable across the prompt, RAG pipeline, orchestrator, and backend
- Comfortable across any stack - you go where the right solution is
- Honest communication - you flag problems early and give direct, candid feedback
- You understand production concerns such as reliability, maintainability, security, observability, latency, and cost
- Real fluency with AI coding tools - genuinely fast, not just 'familiar with'
- Think in workflows, not endpoints - agentic loops, skills, and orchestrated flows; CRUD with an LLM bolted on isn't a system
- Clear judgment about when to trust AI output and when to rewrite it
- Goes beyond using AI - builds skills, workflows, and harnesses, not just prompts
- You understand common AI-system risks such as hallucinations, prompt injection, data leakage, unreliable tool execution, and uncontrolled autonomy
Desired Qualifications
- Fintech or regulated-environment experience - understanding why 'probably fine' isn't acceptable when money is moving
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.