Company Description Nexthink is the leader in digital employee experience management software. The company provides IT leaders with unprecedented insight allowing them to see, diagnose and fix issues at scale impacting employees anywhere, with any application or network, before employees notice the issue. As the first solution to allow IT to progress from reactive problem solving to proactive optimization, Nexthink enables its more than 1,500 customers to provide better digital experiences to more than 25+ million employees. Dual headquartered in Lausanne, Switzerland and Boston, Massachusetts, Nexthink has 9 offices worldwide. #LI-Hybrid Job Description At Nexthink, we are embedding AI agents into the core workflows of our Product organization. We are seeking an AI Agent Engineer to design, build, and continuously improve intelligent agents that augment and automate high-impact product operations activities. This role supports Nexthink's Product organization, serving a group of 30+ people across Product Management, Product Education, Library, and Product Operations. You will operate in a highly autonomous role, owning the architecture, behavior, and quality of AI agents that improve decision-making, reduce manual work, and increase execution speed. You will combine applied AI engineering with strong systems thinking. The focus is not model research, but production-grade agent design, evaluation, governance, and workflow integration. This role requires strong ownership, product empathy, and comfort operating independently in a production environment with real business impact. What you'll do Design and architect AI agents - Design reusable AI agent patterns for Product workflows such as research synthesis, PRD (Product Requirement Document) drafting support, roadmap analysis, operational triage, and knowledge retrieval. - Define agent instructions, tool schemas, guardrails, and structured output contracts. - Architect human-in-the-loop decision boundaries where appropriate. Integrate agents into product workflows - Integrate AI agents into Microsoft 365, Copilot Studio, Power Platform, AWS services, and internal systems. - Define and maintain action interfaces between agents and deterministic systems (APIs, workflows, runbooks). - Ensure reliable orchestration across conversational and workflow layers. Own quality, evaluation, and governance - Define measurable success criteria for agent outputs. - Build lightweight evaluation frameworks and regression testing for prompts and behavior. - Monitor output quality, hallucination risk, cost, and drift over time. - Establish safe usage guidelines and governance boundaries. Operate and improve in production - Monitor agent usage, reliability, and impact. - Optimize performance, token efficiency, and response structure. - Iterate on agent behavior based on real usage patterns and feedback. - Proactively identify new opportunities where AI agents can improve Product workflows. Qualifications Must-have - 6-8+ years of experience building and owning production systems end to end. - Strong system design skills, including event-driven and serverless architectures, with clear trade-off reasoning. - Experience integrating systems through APIs, webhooks, REST, and Graph. - Practical experience designing or integrating AI or LLM-powered workflows in production. - Strong independent ownership and architectural judgment. - Ability to translate ambiguous business needs into structured, scalable AI-enabled solutions. - Excellent collaboration and communication skills. Critical competencies - Prompt and instruction design as structured system artifacts. - Tool and schema design for AI agents. - Evaluation methodology for AI systems (quality metrics, regression testing, failure pattern analysis). - Understanding of LLM failure modes and mitigation strategies. - Experience designing guardrails, structured outputs, and human approval flows. Nice to have - Experience with Microsoft Copilot Studio, Power Platform, or similar low-code orchestration tools. - Experience with AWS services such as Lambda, Step Functions, EventBridge, or Bedrock. - Familiarity with conversational UX design. - Experience embedding AI into internal productivity workflows. At Nexthink, you will join a dynamic, fast-growing team where innovation and ownership are encouraged. This is more than an engineering role-it's an opportunity to shape how we work, scale our impact, and bring AI-powered automation into the heart of our product operations. Additional Information We are the pioneers and trailblazers of a global IT Market Category (DEX) that is shaping the future of how the world works, giving our customers' IT Teams total digital visibility across their enterprise. Our innovative solutions integrate real-time analytics, automation, and employee feedback across all endpoints. This enables our IT teams to solve complex technical challenges, create ever more productive workplaces, and deliver happy, satisfied employees in the digital workplace. With over 1200 employees across 5 continents, Nexthink operates as One Team, connecting, collaborating and innovating to continuously grow. We call our employees 'Nexthinkers' and our commitment to diversity, inclusion, and equity is second to none. We currently have over 75 nationalities working with us, from all cultures and backgrounds, speaking many different languages. If you are looking for a change and like a nice atmosphere, lots of challenges, and having fun while working, this is a great opportunity for you! Check what we offer: - Permanent Contract and a competitive compensation package. - Amazing centrally located offices near the Bernabeu Stadium. - Private Health Insurance (Sanitas) and daily meal vouchers of 11 EUR will be entirely covered by us. - Hybrid work model balancing office and remote work, with a structured approach for new hires to foster connections and onboarding. - Flexible Hours and unlimited vacation (employees have unlimited paid time off on top of the 23 days of holidays we offer) plus 3 company-paid volunteer days. - Up to 25 EUR per month for a gym subscription. - Flexible compensation plan for childcare & public transportation. - ‍ Reimbursement of up to 50% of the cost of English & Spanish classes. - Fresh fruit, cookies, soft drinks and protein shakes at the offie. - Regular company and team events like Pizza talks, Team Building activities, Christmas parties, hosting Meetups at the office and more! - Bonuses for referring successful hires after three months of continuous employment. - We offer a relocation package to people who are coming from another country. Please note that not all the benefits listed above are available for temporary, contract, and internship roles. To ensure you have the most up-to-date information, we recommend checking with your Recruitment Partner.

Role Description We are hiring an AI / GenAI Engineer to build and deploy production agents on Google Vertex AI (now the Gemini Enterprise Agent Platform). You will work end-to-end — from prototyping with Gemini models and RAG, to building multi-agent workflows with the Agent Development Kit (ADK), to deploying on Agent Runtime with proper governance, evaluation, and monitoring. This is a hands-on engineering role with direct client and solution-design exposure. Key Responsibilities - Design, build, and deploy enterprise-grade AI agents on Vertex AI / Gemini Enterprise Agent Platform (Model Garden, Agent Builder / Agent Studio, Agent Engine / Agent Runtime, Vertex AI Pipelines, Model Registry, Endpoints). - Develop GenAI applications using Gemini (3.x family) and other Model Garden models — prompt engineering, function calling, structured output, and model evaluation/tuning. - Build RAG pipelines using Vertex AI Search, Vector Search, RAG Engine, and embeddings; implement grounding against enterprise data sources. - Implement multi-agent orchestration using the Agent Development Kit (ADK), Memory Bank / Sessions, and the Agent2Agent (A2A) protocol; integrate tools via Model Context Protocol (MCP) servers. - Productionize models and agents with solid MLOps practices: CI/CD, Vertex AI Pipelines, model/agent monitoring, observability, and cost optimization. - Integrate AI services with enterprise systems and APIs (REST/gRPC, FastAPI) and wider GCP services (BigQuery, Cloud Run, Cloud Functions, Pub/Sub, GCS, Dataflow, GKE). - Apply enterprise governance and security — IAM, data privacy, and responsible-AI guardrails. - Partner with solution architects and client stakeholders to gather requirements, design solutions, and document deliverables. Qualifications - 4–8 years of software/ML engineering experience, with hands-on Vertex AI / Gemini Enterprise Agent Platform (or equivalent GCP AI) project experience. - Strong Python programming; clean, production-quality code. - Practical experience building GenAI / LLM applications — prompting, RAG, embeddings, vector databases, and model evaluation. - Working knowledge of Google Cloud Platform core services (BigQuery, Cloud Run/Functions, GCS, IAM, Pub/Sub). - Experience deploying and operating models/agents in production (MLOps, containerization with Docker, basic Kubernetes/GKE). - Solid understanding of agentic AI concepts — tool use, multi-agent orchestration, memory, and agent governance. - Strong API design and integration skills (REST/gRPC, FastAPI). - Good communication and the ability to work directly with clients and cross-functional teams. Good-to-Have (Preferred) - Google Cloud certification — Professional Machine Learning Engineer or Professional Cloud Architect. - Experience with the Agent Development Kit (ADK), A2A protocol, and MCP integrations. - Familiarity with orchestration frameworks such as LangGraph, LangChain, or LlamaIndex. - Exposure to other AI stacks (AWS Bedrock, Azure OpenAI, Anthropic Claude) for multi-cloud / multi-model work. - Experience integrating AI with enterprise platforms (NetSuite, Salesforce, ERP/CRM systems). - Background in consulting / client-facing delivery environments. Education - Bachelor's or Master's degree in Computer Science, Engineering, Data Science, or a related field (B.E. / B.Tech / M.E. / M.Tech / MCA). Equivalent practical experience also considered.

• Design, build, and harden agentic workflows that plan and take actions reliably — and understand why agents fail (context loss, compounding errors, no feedback signal) and how to structure tasks so they succeed. • Build retrieval (RAG/search) pipelines that fetch the right client data and ground model outputs in it, integrated into core applications rather than demos. • Select the right model for each task — reasoning model vs. fast instruction model — and be able to justify the trade-off in latency, cost, and quality. • Engineer prompts and context structures appropriate to the model class, including knowing when reasoning models need framing rather than step-by-step hand-holding. • Write evaluations for AI features, because with non-deterministic models “it worked once” is not evidence that it works. • Connect AI tools to internal systems and data sources via APIs or MCP to power real client use cases. • Review and validate AI-generated code and automated workflows critically for correctness, security, and safety. • Collaborate with the Builder and the Integration & Data Engineer to deliver complete, working solutions, and document workflows, prompts, and integrations in Notion.

• Build agent harnesses in Python using LangChain and LangGraph, including tool-calling, structured outputs (Pydantic/JSON schema), retries, streaming, and memory • Package agent harnesses for the AgentCore Runtime with appropriate context, tools, skills, and subagents that fit cleanly into production flows and scenarios • Write the tools and skills agents use: API integrations, SQL queries against Snowflake, Snowflake backed knowledge retrieval with clear contracts and Pydantic validation • Build evaluation harnesses (golden datasets, LLM-as-judge, regression suites) using AgentCore Evaluations, and wire them into CI • Implement guardrails around tool execution: auth scoping, input/output validation, PII and prompt-injection protections, and hallucination mitigation • You own what you ship: prototype, deploy through Amazon AgentCore, monitor traces, and fix it when it breaks • Partner with data engineers on Snowflake backed retrieval patterns (Cortex Analyst and Cortex Search Services) • Contribute to refining our internal engineering patterns as the stack evolves