MR001 – AI & Agentic Systems Engineer
- Location(s):
- Zurich, Switzerland
- Duration:
- 12 months
- Experience:
- Senior
- Start:
- ASAP
- Model:
- Hybrid
Project description
A global professional-services organization is building a secure enterprise agent platform to automate research, document-heavy workflows, and multi-step knowledge tasks while keeping experts in control of critical decisions.
As a mindrush AI & Agentic Systems Engineer, you will join a senior AI engineering team to design and productionize agentic workflows, orchestration layers, and evaluation systems that connect foundation models with enterprise data and business applications.
The focus is production impact, not prototypes: reliable architectures, measurable quality, observability, security, and human-in-the-loop controls will be central to every use case.
Who you'll work with
You will work alongside a mindrush Partner and senior client leaders as part of a carefully curated Liquid Workforce of independent experts. Depending on the mission, your team may include specialists in:
- AI Engineering
- Data Platform
- Cloud & Security
- Product Management
- Domain Experts
We build small, senior teams that combine deep expertise with rapid execution.
Your mission
You will help the client move from ambition to execution by:
- Designing and implementing production-grade agentic workflows and orchestration patterns
- Building RAG, tool-use, memory, and multi-agent components where they add measurable value
- Integrating LLM systems with enterprise APIs, data platforms, and internal applications
- Creating evaluation frameworks for quality, latency, cost, safety, and task completion
- Implementing observability, guardrails, and human-in-the-loop review mechanisms
- Optimizing prompts, context strategies, and model selection across use cases
- Working closely with product and domain experts to move use cases from pilot to scale
Must have
- 5+ years of software engineering experience with strong recent experience in applied AI/LLM systems
- Hands-on experience building agentic or tool-using LLM applications in production
- Strong Python engineering skills and solid software architecture fundamentals
- Experience with RAG, vector search, APIs, model evaluation, and LLM observability
- Understanding of cloud deployment, security, and production reliability
- Ability to work autonomously in a distributed senior team
- Fluent English
Nice to have
- Experience with LangGraph, LlamaIndex, Semantic Kernel, or equivalent orchestration frameworks
- Experience with MCP, structured tool calling, or enterprise agent platforms
- Knowledge of fine-tuning, synthetic data, or model-routing strategies
- Experience in regulated or security-sensitive enterprise environments
- Open-source contributions or a strong applied AI engineering portfolio
Recruitment process.
Our process is designed to be straightforward, transparent and respectful of your time.
-
1. Introduction call
A discussion to understand your background, ambitions and expertise.
-
2. Meet the client
A business conversation focused on your experience, problem-solving approach and client impact.
-
3. Mission matching
If there's a good fit, we'll onboard you on the opportunity aligned with your profile.
