Software Engineer - Agentic Engineering
Swiss Re is hiring a Software Engineer - Agentic Engineering in Bratislava, Slovakia. Level rates it ; you can apply on Swiss Re.
Level's read on this job
- On Level's scale, this software engineer role is Builds AI ●●●●: the job is building AI systems.
- Tools and skills the posting cites include Claude, Claude Code and RAG.
- Level lists 240 other open roles at Swiss Re.
AI in this role
P&C Re Engineering is looking for a Software Engineer to help build and evolve the AI and agentic systems behind our reinsurance business. This is a hands-on engineering role for someone who enjoys shipping production software, is fluent — or eager to become fluent — with agentic coding tools, and wants to work at the frontier of applied AI.
Agentic Engineering builds and runs AI and agentic systems for reinsurance — across Claims, Treaty and Facultative lines — on the platforms the firm already runs. While this is a hands-on engineering role, it rewards a strong product and quality mindset: you will own the software behind a line's AI systems and lead its development toward genuinely agentic systems.
What you will do
As a Software Engineer in the team, you will build, evolve and run the software behind a line's AI systems — the services and workflows that LLM-based agents use. You will work day-to-day with agentic coding harnesses (e.g. Claude Code): breaking work into well-scoped tasks, directing AI agents to build and modify code, and reviewing their output with calibrated scrutiny — spec-first, tested, and accountable for what your agents produce. You will work closely with the Product, Architecture and Domain Delivery organisations.
If you join us, you will for example:
- Maintain, refactor and extend the line's AI applications and services in production
- Build agentic-friendly software: the tools, services and workflows that LLM-based agents call
- Design AI workflows that combine models, prompts, tools, enterprise data, and business logic
- Validate model behavior, outputs, and assumptions from a production and business-use perspective
- Design and maintain evaluation frameworks for AI/LLM systems, including test suites and human evaluation workflows
- Write evaluations and quality checks for agent behavior, and build in grounding and assurance
- Ensure reliability, scalability, cost control, and latency optimization
- Help bring new agentic systems into production
We are a small, senior and hands-on team working at the frontier of applied AI for reinsurance. Our focus on agentic engineering connects us: we invest in the tools and patterns that let a small team deliver outsized impact, and we expect everyone to share what they learn.
About you
Nobody is perfect and meets 100% of the requirements. If you meet many of the criteria below and are excited to build production AI systems with agentic tooling, we would be happy to meet you.
In order to be successful in the role, you bring:
- Strong software engineering: a modern language (Python, TypeScript, or Java / Kotlin), clean code, automated testing, CI/CD
- A Forward Deployed Engineer mindset — a desire to understand the business problem, the impact the solution makes, and to drive pragmatic decisions towards realising it
- API / service / integration engineering
- Familiarity with LLM application patterns (prompting, retrieval-augmented generation, tool / function calling) and an appetite for agentic development
- Comfort working with agentic coding harnesses (e.g. Claude Code) — directing AI agents and reviewing generated code — and in a Linux / cloud environment
- The ability to pick up and improve an existing codebase
- Exposure to Data Science methods in validating AI models
It is a strong plus if you also have:
- Hands-on agentic / LLM application development (agent loops, evaluations, tool design)
- Experience with Palantir Foundry / AIP (valued, not required)
- Insurance or reinsurance domain exposure
- Experience with cloud AI services (e.g. Azure AI)
Even if you do not tick every box, but are eager to grow into this role and work at the frontier of agentic engineering, we encourage you to apply.
Thank you for taking the time to read our job advertisement. We look forward to getting to know you.
For Slovakia the base salary range for this position is between [EUR 2,400] and [EUR 4,100] per month (for a full-time role). The specific salary offered considers:
-
the requirements, scope, complexity and responsibilities of the role,
-
the applicant’s own profile including education/qualifications, expertise, specialisation, skills and experience.
In addition to your base salary, Swiss Re offers an attractive performance-based variable compensation component, designed to recognise your achievements. Further you will enjoy a variety of global and location specific benefits.
Eligibility may vary depending on the terms of Swiss Re policies and your employment contract.
About Swiss Re Corporate Solutions
Swiss Re is one of the world’s leading providers of reinsurance, insurance and other forms of insurance-based risk transfer. We anticipate and manage risks, from natural catastrophes and climate change to cybercrime.
Swiss Re Corporate Solutions is the commercial insurance arm of the Swiss Re Group. We offer innovative insurance solutions to large and midsized multinational corporations from our approximately 50 locations worldwide. We help clients mitigate their risk exposure, whilst our industry-leading claims service provides them with additional peace of mind.
Our success depends on our ability to build an inclusive culture encouraging fresh perspectives and innovative thinking. Swiss Re Corporate Solutions embraces a workplace where everyone has equal opportunities to thrive and develop professionally regardless of their age, gender, race, ethnicity, gender identity and/or expression, sexual orientation, physical or mental ability, skillset, thought or other characteristics. In our inclusive and flexible environment everyone can bring their authentic selves to work and their passion for sustainability.
If you are an experienced professional returning to the workforce after a career break, we encourage you to apply for open positions that match your skills and experience.
Swiss Re is an equal opportunity employer. It is our practice to recruit, hire and promote without regard to race, religion, color, national origin, sex, disability, age, pregnancy, sexual orientations, marital status, military status, or any other characteristic protected by law. Decisions on employment are solely based on an individual's qualifications for the position being filled.
During the recruitment process, reasonable accommodations for disabilities are available upon request. If contacted for an interview, please inform the Recruiter/HR Professional of the accommodation needed.
We may use AI-powered tools to support the review and evaluation of applications for this position. These tools provide additional insights to our recruitment teams, but all hiring decisions are carefully reviewed and made by people. To learn more about how we use AI in recruitment and how we handle your personal data, please review our Data Privacy Statement before applying.
#corso
Keywords:
Reference Code: 139367
How we rate this
Software Engineer - Agentic Engineering at Swiss Re rates 88 out of 100 for how much of the daily work is AI. That makes it Builds AI (AI Level 4 of 4). The level is about AI in the job, not seniority.
Builds AI. The job is building AI systems.
- ●●●● Builds AI80 to 100
- ●●●○ Works on AI60 to 79
- ●●○○ Uses AI40 to 59
- ●○○○ Little AI0 to 39
Levels come from how often the tools, models and workflows of the role are named in the posting itself. Read the description and count the AI tools, models and workflows it names.
Prepare for this job
Built from this posting and from similar jobs on Level.
Skills and AI tools this role asks for
Also common in software engineer jobs at this level
Pay
- Typical software engineer job
- $167k
This posting doesn't list pay. Use the typical software engineer figure when pay comes up. See software engineer jobs
Questions you could be asked
- How would you design a retrieval step so the model answers from real data instead of guessing?
- How do you decide when an AI agent can act on its own versus asking for approval first?
- What are the limits of Claude that you've run into, and how did you work around them?
- What's a project where you used Claude Code hands-on?
- How would you decide a model or AI system is ready to ship?
Adapt your resume
- List these exact terms on your resume: RAG, AI agents, Claude, and Claude Code. An applicant tracking system matches the wording, not the idea.
- Attach one line of real, concrete experience to at least one of them. A tool named with nothing behind it rarely survives a human read.
- Lead with what you built, trained or shipped. This role is judged on the AI system itself, not the tools around it.
Want an expert to read your CV for this job?
Free. Send your CV and the role you want next. You get your review by email within 24 hours.
Get new software engineer jobs (Builds AI ●●●●) by email
One email a week with the new software engineer jobs (Builds AI ●●●●), each rated for how much AI is in the work. No recruiter spam, unsubscribe in one click.
Free. One email a week. Unsubscribe in one click.
Similar roles
Software Engineering roles that build AI, at other companies.
What kind of AI work fits you?
Answer 12 practical questions in about three minutes. Get a simple profile, the work it points to, and live roles to explore next.
Find my next step