Architect and build the agentic systems behind the Investigation Agent, including LangGraph workflows, tool integration, memory, reasoning, and orchestration.
Own context engineering: determine what information the agent sees, when it sees it, and how it's structured to maximize performance and reliability.
Build feedback loops, evaluation frameworks, and tracing infrastructure (Langfuse and beyond) to make agent development measurable and iterative.
Drive key architectural decisions around agent state, long-running workflows, failure recovery, deployment, rollbacks, latency, and cost at scale.
Own complex backend engineering work end-to-end across our stack: Python, FastAPI, Postgres, Redis, Kubernetes, ensuring agent systems are reliable, observable, and production-ready.
Partner with Product, UX, Data Science, and Engineering to shape solutions, provide technical guidance, and align features with the realities of current AI capabilities.
Champion AI-native development practices, leveraging tools like Claude Code, Cursor, and similar coding agents while promoting automation and team-wide adoption.
Help define Hawk’s core engineering standards for agentic products, including testing, evaluation, deployment, monitoring, and trustworthiness.

Deep Python backend expertise and a track record of delivering production systems.
Experience building agentic systems, including workflows, tool integration, context management, memory, and evaluation, using LangGraph, other frameworks, or custom solutions.
Strong understanding of context engineering, prompt design, evaluation, and LLM failure modes, with a focus on building reliable systems at scale.
Solid backend fundamentals across FastAPI (or similar), Postgres, Redis, Kubernetes, observability, and production operations.
Daily user of agentic coding tools such as Claude Code, Cursor, or similar, with practical knowledge of their strengths, limitations, and best practices.
Strong systems thinking and problem-solving skills, with the ability to shape product direction and architecture, not just execute requirements.
Excellent communication and collaboration skills, able to clearly explain technical trade-offs to both technical and non-technical stakeholders.
Nice to have: Production experience with LangGraph (or equivalent agent orchestration frameworks) and Langfuse (or equivalent LLM observability/eval tooling).
Prior experience in Anti-Financial Crime (AML, fraud, compliance, or investigations tooling) — or a deep curiosity to go learn the domain fast.

Career Growth: Accelerate your professional journey by working with cutting-edge technologies in a truly global environment.
Holidays: Enjoy extra vacation days to recharge and unwind.
Workation: Work from anywhere in the world for up to 45 days per year.
Flexibility: Benefit from hybrid working options for a healthy work-life balance.
Workplace: A modern, pet-friendly office equipped with parking and plenty of snacks to keep you fueled and productive.
High-Spec Hardware: Brand-new, high-performance equipment provided to support your work from day one.
Team Environment: A dynamic, collaborative, and friendly working atmosphere.
Perks: Stay balanced with our wellness program, enjoy additional health insurance, plan for the future with 3rd-pillar pension benefits, and perform at your best with high-spec hardware.

Senior GenAI Engineer

Key skills