Senior AI Engineer - Agentic AI & Copilot

Why Billennium? Billennium is a global technology company with over 20 years of experience, committed to innovation and empowering businesses. As an employer, we offer a supportive, growth-focused environment where collaboration and creativity thrive. Join us to shape the future of technology together. Role Summary: We are looking for a Senior AI Engineer to design, build and deliver production-grade AI applications across agentic AI, LLM-powered solutions, RAG, AI assistants and enterprise automation. This is a hands-on engineering role for someone who enjoys taking AI solutions from concept to production. You will work across the full delivery lifecycle - from understanding business needs and designing the solution architecture, through development and integration, to deployment, monitoring and continuous improvement. You will build AI agents, intelligent assistants, RAG-based applications, LLM-powered services and automation workflows, integrating them with enterprise systems and existing business processes. We are looking for an AI-native engineer with strong software engineering foundations who can combine AI expertise with backend development, APIs, cloud technologies and production engineering. You should be comfortable working directly with business and technical stakeholders and turning business requirements into scalable, pragmatic solutions. Our technology environment includes Python, FastAPI, LLMs, agentic frameworks, RAG and vector search, cloud platforms, Docker, Kubernetes, Terraform, APIs and modern AI observability and evaluation tools. What You Will Do: AI & Agentic Applications Design and develop LLM-powered applications and AI agents for real-world business use cases.Build agentic workflows, including tool use, multi-step reasoning, orchestration and integration with external services.Develop conversational AI, AI assistants and other user-facing AI applications.Integrate LLMs from different providers and select appropriate models and approaches based on business and technical requirements.Apply effective prompt engineering, context management and guardrails to improve the quality, reliability and safety of AI applications.RAG & Knowledge-Driven AI Design and implement RAG solutions using embeddings, vector search and structured/unstructured enterprise data.Develop retrieval strategies and improve chunking, metadata, embeddings, context and retrieval quality.Work with vector databases and search technologies such as PostgreSQL/pgvector, OpenSearch, or equivalent solutions.Explore advanced retrieval approaches, including hybrid or graph-based RAG, where appropriate.Continuously improve the accuracy and relevance of AI-generated responses.Backend & AI Engineering Build production-grade Python services and APIs, with FastAPI or similar frameworks.Design scalable backend architectures and integration layers for AI applications.Integrate AI services with enterprise systems through APIs, webhooks, events and other integration mechanisms.Build reliable microservices and cloud-native components supporting AI workloads.Ensure solutions are scalable, maintainable, secure and production-ready.Cloud, Deployment & Automation Containerize and deploy AI applications using Docker and Kubernetes or equivalent cloud-native technologies.Work with cloud platforms such as AWS, Azure or GCP.Contribute to infrastructure and deployment automation using technologies such as Terraform.Build and maintain CI/CD pipelines for AI applications and services.Integrate AI capabilities with business automation platforms and workflow orchestration tools where appropriate.AI Quality, Evaluation & Observability Implement monitoring, telemetry, tracing and observability for production AI applications.Establish evaluation approaches to measure the quality and reliability of AI systems.Build regression and evaluation processes for LLM, RAG and agentic applications.Monitor and improve key metrics such as accuracy, latency, cost, reliability, safety and user adoption.Implement appropriate guardrails and quality controls for enterprise AI solutions.Business Collaboration & Delivery Work directly with business stakeholders and clients to understand requirements and translate them into technical solutions.Contribute to solution architecture, technical design and delivery planning.Make pragmatic technical decisions that help teams move quickly from prototype to production.Communicate technical concepts clearly to both technical and non-technical stakeholders.Identify opportunities to reuse existing AI components and patterns across different solutions and projects.Reusable AI Solutions Create reusable AI agents, RAG components, integration patterns, prompts and technical blueprints.Contribute to internal frameworks, libraries and engineering standards.Share knowledge and help establish scalable approaches to building AI solutions across multiple projects. Role Requirements: 3-5+ years of experience in AI/ML engineering, software engineering or a closely related field.Proven experience building and deploying AI/LLM-powered applications to production, beyond prototypes and POCs.Strong Python development skills and experience building production APIs and backend services.Hands-on experience developing AI agents, LLM applications or agentic workflows.Solid practical experience with RAG, embeddings and vector search.Experience with at least one modern LLM/AI application framework, such as LangChain, LangGraph, Haystack, LlamaIndex or an equivalent technology.Experience integrating LLM services and AI capabilities with external systems and enterprise applications.Good understanding of software architecture, APIs, microservices and cloud-native development.Experience with at least one major cloud platform (AWS, Azure or GCP).Experience with Docker and preferably Kubernetes or an equivalent container orchestration platform.Practical experience with CI/CD, infrastructure automation or DevOps practices.Experience implementing AI observability, evaluation, monitoring or quality assurance for production systems.Ability to work independently and take ownership of AI solutions from technical design through production delivery.Strong communication skills and confidence working directly with clients, product teams and business stakeholders. Nice to Have: Experience with Microsoft Copilot, Copilot Studio or other enterprise AI assistant platforms.Experience with RPA, workflow automation or orchestration platforms, such as UiPath, n8n or equivalent technologies.Experience with AWS Bedrock, Azure OpenAI, Microsoft AI ecosystem or similar enterprise AI platforms.Experience with MCP (Model Context Protocol) or comparable approaches to connecting AI agents with tools and external systems.Experience with graph-based RAG, knowledge graphs or advanced retrieval techniques.Experience with PostgreSQL/pgvector, OpenSearch, Neo4j or similar technologies.Experience with AI observability and evaluation platforms such as Langfuse, MLflow, Phoenix, RAGAS, DeepEval or equivalent tools.Experience with Terraform and Kubernetes/AKS/EKS.Experience building AI solutions in enterprise, regulated or client-facing environments.Ability to contribute to the UX of AI-powered applications when needed. Perks and benefits (our offer): Comprehensive benefits - enjoy Udemy for Business, private medical care, Multisport card, veterinary package, language lessons, and shopping vouchers.Career growth - access opportunities for professional development and learning, including perks related to our official partnerships with global IT giants: Microsoft, AWS, Snowflake, Salesforce & more.Innovative environment - be part of a forward-thinking and growth-oriented workplace.Engaging community - Work with passionate professionals and participate in team-building events, hackathons, and CSR initiatives to make an impact beyond work.Team-building events including our company tradition (annual company event in Mazury).A pleasant surprise to start your journey with us in the form of a welcome pack.