C

CFC

Cyber risk underwriting through MGA platform

Senior Software Engineer - AI & ML

AI Application EngineeringUpdated on Nov 13
Full-timeLondon, UKNo salary listedHybrid

About the Job

Requirements

  • Hands-on experience building LLM-based agents or agentic systems in production, ideally using LangGraph, LangChain, or equivalent systems.
  • A strong understanding of real-world agent failure modes, including non-determinism, tool failures, runaway loops, cost, and latency, and how to engineer around them.
  • At least 5 years of professional software development experience in Python or another backend language such as Go, Java, or C#. Candidates whose main language is not Python need working knowledge sufficient to transfer their skills quickly.
  • Strong experience with asynchronous and concurrent programming and a rigorous approach to unit and integration testing.
  • Day-to-day experience delivering software with AI coding agents while maintaining a high bar for the code they produce.
  • Experience designing systems end to end, including service boundaries, data flows, and failure modes, and making and explaining architectural trade-offs.
  • Strong relational database and data modelling experience, including schema design, query performance, transactions, concurrency, and safe schema migrations; PostgreSQL is used.
  • Experience building distributed, asynchronous microservices using message brokers such as Azure Service Bus, with understanding of at-least-once delivery, idempotency, and dead-letter handling.
  • Experience building clear, well-documented RESTful APIs; FastAPI is used.
  • Strong cloud and infrastructure-as-code experience. Azure and Terraform are used, and hands-on infrastructure-as-code experience is essential.
  • Experience with Docker and production container platforms such as Azure Container Apps, Kubernetes, GKE, or ECS, alongside CI/CD workflows and YAML pipeline definitions.
  • Clear communication, pragmatic judgement, and the confidence to work independently, influence technical decisions, and mentor other engineers.

Responsibilities

  • Design, build, and run production AI agents that automate multi-step underwriting decisions over unstructured data.
  • Build the agent runtime, including orchestration, durable state, retries, and long-running workflows that recover cleanly from failure.
  • Develop the tools, APIs, and data services that agents call, creating clear contracts, predictable failure modes, and full auditability.
  • Engineer guardrails, human-in-the-loop checkpoints, and fallbacks for high-stakes automated decisions.
  • Instrument, monitor, and troubleshoot agents and services in production, including tracing, cost, latency, and decision logs, and work with machine learning engineers to turn insights into evaluations and improvements.
  • Help drive system design and architectural decisions for agents and related services.
  • Design and evolve the data models and database schemas supporting submissions, agent runs, decisions, and audit trails.
  • Provision and manage cloud infrastructure through Terraform and contribute to high production standards across agent-generated code and tests.
  • Work with business, product, and engineering teams to set delivery cadence, manage expectations, and make pragmatic decisions about where additional engineering quality adds value.
  • Support other engineers’ development through code reviews, best-practice guidance, and knowledge sharing.

Desired Qualifications

  • Experience building agents for high-stakes or regulated decision-making.
  • Experience working with data scientists on non-deterministic systems.
  • Experience using Databricks.
  • Experience working within insurance.

About the Company

CFC

Cyber risk underwriting through MGA platform

CFC Underwriting is a specialist insurance provider operating as a managing general agent (MGA) that underwrites on behalf of a panel of carriers, focusing on emerging and specialty risks with a strong emphasis on cyber. It uses a proprietary global insurance platform powered by data science to streamline underwriting across a portfolio of 50+ products, including cyber and professional liability, with an in-house incident response team adding comprehensive cyber risk management. It differentiates itself through its early focus on cyber, large in-house claims and incident response capabilities, and a global broker-driven distribution model. Its goal is to deliver fast, precise underwriting and robust risk management for technology-related and other specialty risks worldwide.

Company size
1,001-5,000
Company stage
Not listed
Total funding
Not listed
Headquarters
London, United Kingdom
Founded
1999

Recently Posted Jobs

Explore more opportunities at CFC

See more jobs