Staff AI Engineer - Architecture skills
Shift Technology is hiring a Staff AI Engineer - Architecture skills in Paris, France. Level rates it ; you can apply on Shift Technology.
Level's read on this job
- On Level's scale, this AI engineer role is Builds AI ●●●●: the job is building AI systems.
- Some of the work can be done remotely, according to the posting.
- The posting mentions OpenAI, LlamaIndex and LangGraph among its tools and skills.
- Level classes it as a senior role.
- Shift Technology has 10 other open roles on Level.
AI in this role
Lead the architecture and development of production-ready AI agentic systems and LLM orchestration layers as a Staff AI Engineer.
Shift delivers AI agents that transform insurers' most critical work. By combining deep industry expertise and unmatched data resources, Shift provides proven results that have earned the trust of hundreds of the world's leading insurers. Our insurance-grade AI is accurate, explainable, and secure—empowering human experts to move with unmatched speed, total confidence, and a renewed focus on the people they serve.
Your browser does not support the video tag.
Our culture is built on innovation, trust, and a drive to transform the insurance industry through our SaaS platform. We come from more than 50 different countries and cultures and together we are creating the future of insurance.
Learn more at www.shift-technology.com
ABOUT THE ROLE
At Shift, we are building the next generation of AI-driven platform capabilities. We are looking for an experienced, hands-on Staff AI Engineer to serve as the technical anchor for our AI capabilities; someone who is deeply passionate about building, prototyping, and scaling modern AI/LLM systems, while helping shape our broader AI engineering strategy.
This is a high-impact, high-visibility role for a senior builder who excels at the intersection of cutting-edge AI technologies (Agentic frameworks, LLM orchestration, MCP, GenAI) and production-grade software engineering. You will work directly with data scientists, software engineers, and product leaders to design, prototype, and ship state-of-the-art AI systems into production.
If you are a senior AI engineer looking for the next step in your career -where you can drive architectural strategy and mentor others without giving up hands-on coding and building- this role is for you.
WHAT YOU'LL DO
- Build & Architect Agentic Systems (Hands-On): Lead by doing. Design, prototype, and build production-ready agentic workflows, custom orchestration layers, and tool-calling integrations using modern frameworks.
- Bridge AI & Production Engineering: Move AI prototypes into robust, production-grade microservices on Azure. Ensure AI components are scalable, low-latency, and well-integrated into the broader tech stack.
- Implement Next-Gen AI Standards: Experiment with and integrate emerging paradigms into our production stack, including Model Context Protocol (MCP), advanced RAG patterns, vector pipelines, and structured LLM outputs.
- Drive AI Quality & LLMOps: Establish and implement operational frameworks for experiment tracking, evaluations, prompt engineering, latency optimization, token budget governance, and model observability.
- Influence & Upskill: Act as a technical mentor for agent-focused engineering squads. Lead technical design reviews, set coding standards, and help elevate the team's AI engineering capabilities.
- Stay at the Cutting Edge: Continuously benchmark new models, AI tools, and architectures, translating relevant breakthroughs into practical, value-driving implementations at Shift.
WHAT WE ARE LOOKING FOR
We are seeking a seasoned AI engineer who combines deep, practical expertise in modern GenAI/LLM ecosystems with strong backend software engineering skills.
Deep AI & Agentic Expertise:
- Hands-On Agentic Frameworks: Proven experience building with frameworks like Microsoft Agent Framework, LangGraph, LlamaIndex, OpenAI Agents SDK, or custom orchestration frameworks.
- LLM Patterns & Tooling: Practical experience with Model Context Protocol (MCP), tool/function calling, structured LLM outputs, and complex RAG pipelines (vector retrieval, hybrid search, embeddings).
- LLMOps & Observability: Experience with evaluation frameworks, prompt engineering, tracing, context window optimization, and compute/token governance in production.
Production Engineering & Stack:
- Programming: High proficiency in Python (required for AI ecosystem work) paired with strong experience in OOP.
- Cloud & APIs: Experience building and scaling backend microservices and REST/OpenAPI endpoints in enterprise cloud environments (specifically Azure).
- Data & Events: Familiarity with vector databases, relational databases, and event-driven patterns (e.g., Azure Service Bus, Kafka).
- Engineering Rigor: Comfortable with containerization (Docker, Kubernetes), CI/CD, testing methodologies, and Infrastructure as Code (Terraform or Bicep).
HOW YOU WORK
- Jump in and get things done: You are a proactive builder who loves turning ambitious ideas into working code. You don't wait for permission to solve hard problems.
- Make things simpler: You can break down complex AI concepts and architectures into clear, executable steps for engineers, data scientists, and non-technical partners alike.
- Test & learn new things: You are genuinely obsessed with the fast-moving AI landscape. You constantly experiment with new models, libraries, and papers, and know how to extract real product value from the hype.
- Communicate with impact & help others grow: You lead by example and collaboration, upskilling team members through pair programming, code reviews, and pragmatic design discussions.
#LI-RH1 #LI-REMOTE
To support our permanent, full time employees at every stage of their careers and lives, we provide a competitive total rewards and benefits package. Here are the global benefits we’d like to highlight:
- Flexible remote and hybrid working options
- Competitive Salary and a variable component tied to personal and company performance
- Multiple Learning and Development opportunities, including Focus Fridays, a half-day each month to focus on learning and personal growth
- Generous PTO and paid holidays
- Mental health benefits
- 2 MAD Days per year (Make A Difference Days for paid volunteering)
Additional benefits may be offered by country, based on your eligibility - ask your recruiter for more information. Intern and Apprentice positions may receive some of these benefits - ask your recruiter for more details.
AI tools are used to help review applications for this role. Read our AI in Recruitment Notice for what the AI considers, how to request a human review, and our most recent bias audit.
At Shift we strive to be a diverse and inclusive workforce. We welcome applications from and hire people who will contribute to the diversity of our company, without regard to race, color, religion, marital status, age, national or ethnic origin, physical or mental disability, medical condition, pregnancy, genetic information, gender identity or expression, sexual orientation, or other non-merit criteria. Shift Technology is committed to providing reasonable accommodations for qualified individuals with disabilities in our application and employment process. Should you require accommodation, please email accommodation@shift-technology.com and we will work with you to meet your accessibility needs.
Please be aware of scammers and only trust correspondence that comes from emails ending in "shift-technology.com". We will never do initial outreach to you via Whatsapp/Text/SMS, never ask for banking information or personal identification numbers (ex. Social Security Number) as part of our recruitment process.
Shift Technology does not accept unsolicited CVs from recruiters or employment agencies in response to the Shift Technology Careers page or a Shift Technology social media post. Any unsolicited CVs, including those submitted directly to hiring managers, are deemed to be the property of Shift Technology.
How we rate this
Staff AI Engineer - Architecture skills at Shift Technology rates 95 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 AI engineer jobs at this level
Pay
- Typical AI engineer job
- $183k
This posting doesn't list pay. Use the typical AI engineer figure when pay comes up. See AI engineer jobs
Questions you could be asked
- How do you structure and test a prompt to get consistent output from a language model?
- 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's a project where you used OpenAI hands-on?
- Walk me through how you've used LlamaIndex in your day-to-day work.
Adapt your resume
- List these exact terms on your resume: Prompt engineering, RAG, AI agents, OpenAI, and LlamaIndex. 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.
Get your CV reviewed before you apply
Send your CV and the role you want next. Your review arrives by email within 3 days.
Get new remote AI engineer jobs (Builds AI ●●●●) by email
One email a week, each job rated for how much AI is in the work. No recruiter spam, unsubscribe in one click.
Free.
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