We are looking for an engineer who can take ownership of a solution from understanding the business problem through production delivery and continuous improvement.
AI-assisted development tools are a core part of how you work. You use them daily, critically, and effectively to improve the quality and speed of software delivery.
You will report to a Domain Architect and work closely with senior engineering, product, and business leaders on AI initiatives and other high-impact challenges.
You will contribute across the full lifecycle: problem definition, solution design, implementation, evaluation, deployment, monitoring, and production support.
What youll do:
Own the full loop - understand the problem, define the solution, architect it, ship it, monitor it. No one hands you a spec
Build with AI as your primary tool - Claude Code, Cursor, whatever gives the most leverage; do in a day what used to take a team a week
Co-design with stakeholders and the business - decision logic, risk thresholds, success metrics
Build the evaluation harness before you ship - if you cant measure it, its not done
Own production from day one - monitoring, alerting, observability; youre on call for what you build
Raise the bar - in design reviews, in code, and in how the team works
Requirements: At least 7 years of experience as a backend engineer
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 dont 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.
AI fluency
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 isnt 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.
Good to have :
Fintech or regulated-environment experience - understanding why "probably fine" isnt acceptable when money is moving
This position is open to all candidates.