Senior Agentic AI Engineer

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 Platform Engineer who can rapidly build, test, and deliver production‑grade AI solutions across LLM gateways, agentic workflows, RAG pipelines, and enterprise automation layers.This is a hands‑on, execution‑first role focused on shipping real value to users quickly, then hardening solutions through evaluation, observability, CI/CD, and enterprise‑grade controls. You will work closely with business stakeholders to reduce delivery bottlenecks and make pragmatic technical decisions that keep momentum high.You will be part of a highly standardized, modern AI stack and contribute to building reusable, scalable AI components that can be deployed consistently across enterprise environments. Core Responsibilities: Agentic & RAG DeliveryDesign and build agentic workflows using LangChain and LangGraph, including tool‑using agents and multi‑step orchestrationImplement RAG pipelines using Postgres + pgvector (default), with Redis‑based caching where appropriateOptimize context strategies (chunking, metadata, retrieval tuning) to improve accuracy and reduce hallucinationsMicrosoft Copilot EnablementBuild and integrate AI assistants and copilots within Microsoft 365 workflowsWork hands‑on with Microsoft Copilot and Copilot Studio, connecting copilots to enterprise data and workflows within governance constraintsUse VS Code and GitHub Copilot as standard acceleration tools in daily deliveryAutomation & Execution LayerBuild and integrate UiPath RPA workflows to execute business processes reliably (queues, triggers, exception handling)Orchestrate business‑triggered workflows using n8n where low‑code orchestration is appropriateIntegrate AI services with UiPath, n8n, and enterprise systems via APIs and webhooks, ensuring traceability and reliabilityQuality, Evaluation & Observability (Non‑Negotiable)Implement telemetry, tracing, and monitoring using Langfuse (or equivalent)Build evaluation suites and regression gates using DeepEval, RAGAS, and optionally MLflow or PhoenixOwn measurable improvements in accuracy, latency, cost, safety, and adoptionProduction Readiness & ScalePackage and deploy containerized services using Docker and Kubernetes (AKS)Build and maintain CI/CD pipelines for AI services (tests, evaluations, deployments)Create reusable building blocks: agent templates, RAG modules, prompt/context patterns, and integration adaptersContribute to internal libraries and blueprints to ensure solutions are repeatable across clients Role Requirements: Technical SkillsStrong experience building production AI systems (not only POCs)Hands‑on expertise with LangChain / LangGraph, RAG architectures, and LLM‑based systemsExperience with LLM gateways and routing concepts (Portkey or similar strongly preferred)Solid Python development skills (FastAPI or similar frameworks)Strong knowledge of Docker, Kubernetes (AKS), and TerraformExperience with CI/CD pipelines, secrets management, and enterprise DevOps practicesFamiliarity with Postgres + pgvector, Redis, and API‑based integrationsExperience with UiPath and/or n8n is a strong plus What We Offer: Opportunity to work in a collaborative, agile product team balancing maintenance and innovationSupportive work environment with strong team collaborationWork-life balance and flexible working arrangements, including remote work optionsClear career development path with mentoring and coaching programsAccess to private healthcareParticipation in international projects and training programsUnlimited learning opportunities (e.g., Azure Academy, Pluralsight, and more)