• Implementing Azure OpenAI API for applications. • Implementing RAG systems. • Working with open source models to fine-tune and apply them for clients. • Experimenting with different ML techniques. • Creating PoC, MVP of AI applications. • Researching new techniques, models and approaches to apply AI in retail, healthcare, finance and general industries.

• Buscar um(a) Engenheiro(a) de IA que tenha paixão por soluções inovadoras e experiência prática no desenvolvimento de soluções de ponta. • Atuar em projetos de Inteligência Artificial Generativa no ecossistema Google Cloud Platform, colaborando com squads de desenvolvimento para construir, otimizar e escalar agentes autônomos e soluções de IA de última geração. • Desenvolvimento de Agentes: Projetar e desenvolver agentes autônomos inteligentes utilizando frameworks modernos como LangChain e LangGraph, criando fluxos complexos que combinem múltiplas ferramentas. • Arquitetura de Agentes: Implementar comunicação entre agentes utilizando arquiteturas alinhadas com a necessidade de negócios, integração de HiTL (Humans in The Loop), gerenciar o ciclo de vida e orquestração de agentes e integrar com ferramentas externas utilizando MCP servers. • IA Conversacional: Criar agentes conversacionais sofisticados com memória de curto e longo prazo, incluindo resumos de sessões anteriores, rastreabilidade de pautas e preferências do cliente. • Integração e Ecossistema Google: Utilizar o Google ADK, LangGraph e ou bibliotecas similares para construir, integrar e otimizar soluções de IA robustas. • Modelagem e Avaliação: Experimentar, integrar e avaliar diferentes LLMs (OpenAI, Gemini, DeepSeek, Cohere), utilizando frameworks de avaliação focados em LLM Evals para medir performance e garantir a qualidade dos produtos. • RAG e Dados: Implementar técnicas avançadas de RAG, incluindo Hybrid Search, reranking, e estratégias de auto-otimização como Corrective RAG (Self-Reflection), conectando os agentes a dados corporativos (ex: GCP) e estruturando bancos vetoriais. • Coleta de Informação: Utilizar mecanismos de web scraping inteligente e parsing de documentos para coletar e processar informações externas. • Automação e Pipelines: Integrar agentes a APIs (Requests, FastAPI) e serviços para executar ações e automações, além de montar pipelines de experimentação, versionamento e publicação de modelos. • Colaboração: Atuar junto às áreas de negócio para entender necessidades e transformá-las em soluções práticas utilizando agentes de IA.

We're Celonis, the global leader in Process Intelligence technology and one of the world's fastest-growing SaaS firms. We believe there is a massive opportunity to unlock productivity by placing AI, data and intelligence at the core of business processes - and for that, we need your help. Care to join us? Role Description As an Applied AI Engineer specializing in the Public Sector, you are pushing the envelope in solving critical operational challenges for State and Local Government agencies. You will be working with our most strategic public sector clients, understanding their unique objectives—from enhancing citizen services and modernizing legacy systems to optimizing grant management and regulatory compliance—and building Celonis solutions using the world’s leading Process Intelligence (PI) platform in combination with top AI and ML technology partners, such as Microsoft, OpenAI, and Databricks. With Celonis’ Process Intelligence (PI) platform, we feed operational context to AI so it understands the complex realities of government operations (breaking down agency silos) and enables agencies to industrialize AI. This unlocks real ROI on AI deployments, maximizing taxpayer value at scale. There is no AI without PI. You will prototype these solutions, demonstrate their value to government CIOs and Agency Directors, and ensure successful implementation, adoption, and value realization to increase the footprint of Celonis across state and local governments. Key Responsibilities: - AI Discovery & Solutioning: Understand public sector AI strategies and specific agency challenges (e.g., benefits administration backlogs, procurement bottlenecks, public safety resource allocation, or permitting delays). As a Celonis product and government domain expert, find the best problem-solution fit and translate agency requirements into innovative solutions that deliver measurable public impact. - Pre- and Post-Sales Execution: Actively drive the full customer lifecycle within the public sector. Lead technical discovery and capability demonstrations during the complex government pre-sales and procurement (RFP) cycles, and remain deeply involved post-sale to guide implementation, ensuring agreed value and adoption thresholds are successfully met. - Hackathons & Prototyping: Think out of the box, have a „can-do“ attitude, and don’t shy away from complex legacy processes. Leverage cutting-edge AI technologies to rapidly build creative prototypes in agency hackathons, solving critical pain points to improve constituent experiences. - Agentic Process Transformation: Support our government customers in achieving real value out of AI deployments at scale, enabling a fundamental shift from traditional, rigid, paper-heavy workflows to the use of autonomous AI agents empowered by our Celonis Process Intelligence Platform (e.g., intelligent case triaging or automated compliance checks). - Proof Projects: End-to-end execution of critical Proof-of-Value projects. This includes architecting and delivering secure, scalable LLM/agent systems with RAG, tools, and guardrails, while seamlessly integrating with government enterprise data, identity protocols, and stringent compliance/security frameworks (e.g., StateRAMP, HIPAA, CJIS). - Domain & Industry Leadership: Serve as the internal and external technical subject matter expert for the State & Local Government vertical, scaling knowledge across the organization regarding agency processes and public sector nuances. Requirements: - 5+ years of experience leading technical pre-sales and post-sales engagements specifically within the Public Sector (State & Local Government). This includes navigating government procurement cycles, building compelling ROI business cases for public funds, and guiding technical implementations through to constituent value realization. - Deep understanding of business processes native to state and local governments (such as Health & Human Services, Procurement, Finance, DMV operations, or Public Safety) with the ability to translate high-level policy or agency needs into specific, impactful AI use cases. - Expertise in generative AI techniques like RAG, few-shot learning, prompt engineering, multi-agent orchestration, multimodal understanding, or fine-tuning used to build high-impact use cases (e.g., intelligent constituent-facing chatbots, automated processing of policy documents, or grant application analysis). - Solid knowledge of Python and common ML libraries (such as LangChain, pandas, pydantic, sklearn, PyTorch) as well as data engineering tools and technologies. - Strong presentation skills to both internal and external stakeholders (including elected officials, agency directors, and IT leadership), whether leading technical whiteboarding sessions or formal readouts and demos. - Bachelor’s Degree required; Master's Degree in computer science, engineering, mathematics, or related fields, or equivalent work experience preferred. Nice to have (big plus): - Hands-on experience building agentic systems using LLM orchestration, RAG, function calling, and prompt engineering, while ensuring safety through rigorous evaluations and guardrails suited for highly scrutinized public sector environments. - Experience in deploying and monitoring models at scale within government-compliant cloud environments (e.g., AWS GovCloud, Azure Government). - Working knowledge of tools in the LLM ecosystem such as LangChain, LlamaIndex, or other OSS packages. Visa sponsorship is not offered for this role. Learn More about Value Engineering at Celonis Here The base salary range below is for the role in the specified location, based on a Full Time Schedule. Total compensation package will include base salary + bonus/commission + equity + benefits (health, dental, life, 401k, and paid time off). Please note that the base salary range is a guideline, and that the actual total compensation offer will be determined based on various factors, including, but not limited to, applicant's qualifications, skills, experiences, and location. The base salary range below is for the role in California, based on a Full Time Schedule. $145,000—$170,000 USD What Celonis Can Offer You: - Pioneer Innovation: Work with the leading, award-winning process mining technology, shaping the future of business. - Accelerate Your Growth: Benefit from clear career paths, internal mobility, a dedicated learning program, and mentorship opportunities. - Receive Exceptional Benefits: Including generous PTO, hybrid working options, company equity (RSUs), comprehensive benefits, extensive parental leave, dedicated volunteer days, and much more. Interns and working students explore your benefits here. - Prioritize Your Well-being: Access to resources such as gym subsidies, counseling, and well-being programs. - Connect and Belong: Find community and support through dedicated inclusion and belonging programs. - Make Meaningful Impact: Be part of a company driven by strong values that guide everything we do: Live for Customer Value, The Best Team Wins, We Own It, and Earth Is Our Future. - Collaborate Globally: Join a dynamic, international team of talented individuals. - Empowered Environment: Contribute your ideas in an open culture with autonomous teams. About Us: Celonis makes processes work for people, companies and the planet. The Celonis Process Intelligence Platform uses industry-leading process mining and AI technology and augments it with business context to give customers a living digital twin of their business operation. It’s system-agnostic and without bias, and provides everyone with a common language for understanding and improving businesses. Celonis enables its customers to continuously realize significant value across the top, bottom, and green line. Celonis is headquartered in Munich, Germany, and New York City, USA, with more than 20 offices worldwide. Get familiar with the Celonis Process Intelligence Platform by watching this video. Celonis Inclusion Statement: At Celonis, we believe our people make us who we are and that “The Best Team Wins”. We know that the best teams are made up of people who bring different perspectives to the table. And when everyone feels included, able to speak up and knows their voice is heard - that's when creativity and innovation happen. Your Privacy: Any information you submit to Celonis as part of your application will be processed in accordance with Celonis’ Accessibility and Candidate Notices By submitting this application, you confirm that you agree to the storing and processing of your personal data by Celonis as described in our Privacy Notice for the Application and Hiring Process. Please be aware of common job offer scams, impersonators and frauds. Learn more here.

• Design and develop end-to-end NLP pipelines — from classical text processing to state-of-the-art LLM-powered architectures • Build and maintain systems for intent detection, NER, entity extraction, and text classification, both standalone and as components feeding into larger LLM workflows • Design and optimize Retrieval-Augmented Generation (RAG) systems — chunking strategies, vector store architecture, hybrid search (dense + sparse), and re-ranking pipelines • Work with embedding models for semantic search, document retrieval, and intent classification in contact center contexts • Design and implement agentic architectures — tool use, function calling, multi-step reasoning, and orchestration with frameworks like LangChain, LlamaIndex, or custom-built solutions • Develop memory and context management strategies — short-term conversation memory, long-term user context, and context window optimization for multi-turn interactions • Evaluate and benchmark models rigorously: hallucination detection, faithfulness scoring, latency/token cost tradeoffs, and continuous performance monitoring • Integrate AI components into scalable, production-ready microservices with a focus on low-latency inference pipelines • Collaborate with product and engineering to design new AI-powered features and drive innovation across the platform