TL;DR

AI Engineer (Fintech): Develop intelligent financial assistant systems focusing on agentic architectures, evaluation infrastructure, safety, and observability. Focus on designing reliable measurement systems, implementing guardrails, and collaborating with cross-functional teams to improve customer-facing fintech products in a regulated environment.

What you will do

  • Develop and maintain agentic architectures including tool use, multi-step reasoning, orchestration, and failure recovery.
  • Design and maintain evaluation infrastructure with offline test suites, golden datasets, and regression harnesses.
  • Implement safety measures such as hallucination detection, refusal strategies, and factual grounding.
  • Run online and offline experiments (canary, A/B) to validate improvements in user outcomes.
  • Ensure observability by tracing LLM calls, monitoring quality drift, latency, and cost in production.
  • Collaborate with backend, mobile, and other LLM engineers to ship reliable improvements and maintain production health.

Requirements

  • English: B1 or higher required for effective communication with an international team
  • Strong classical ML fundamentals and understanding of model internals.
  • Experience with search and retrieval techniques (dense/sparse/hybrid, reranking, query understanding).
  • Practical experience with agentic architectures and safety-first thinking in production ML systems.
  • Expertise in Python and familiarity with open-source tools for RAG applications.
  • Production ML ownership including observability, latency budgets, cost tracking, and regression detection.

Nice to have

  • Experience delivering business-critical ML/AI applications for customer-facing products.
  • Fine-tuning or distillation of LLMs for production use cases.
  • Experience deploying open-source models (Llama, Mistral) in private/on-premise environments.
  • Experience in fintech, banking, or regulated domains.