Role Description Du baust produktive KI-Systeme (LLM, RAG, Agenten) für große Kunden im öffentlichen Sektor. Kein Prototyp für die Schublade, sondern Software, die im Regelbetrieb läuft. Unsere Kunden sind IT-Dienstleister im öffentlichen Sektor, ein reguliertes Umfeld mit hohen Ansprüchen an Datenschutz und Betriebssicherheit. Dort baust du KI-Lösungen in bestehenden Branchenlösungen ein: - Dialogsysteme - Semantische Suche - RAG-Pipelines - Agenten Alles im echten Produktivbetrieb für viele Nutzer. Projektsprache ist Deutsch. Ein Wort zu Remote: Der Alltag läuft remote-first innerhalb der DACH-Region. Ab und zu bist du vor Ort, den Rest der Zeit arbeitest du von dort, wo du gut arbeitest. Qualifications - Mindestens 3 Jahre Berufserfahrung als Machine Learning Engineer in Konzeption, Entwicklung, Implementierung und Optimierung skalierbarer ML-Lösungen. - Mindestens 2 Jahre Erfahrung in agilen Entwicklerteams. - Deutsch mindestens auf C1-Niveau in Wort und Schrift, nachweisbar über ein Sprachzertifikat oder als Muttersprache. - Abgeschlossenes Studium der Informatik, Wirtschaftsinformatik oder eine vergleichbare Ausbildung, nachweisbar über Zeugnis oder Eigenerklärung. Requirements - Vektorsuche und semantische Indexierung in Vektordatenbanken, idealerweise Milvus. - Backend-Entwicklung mit Python, vorzugsweise FastAPI. - LLM-Orchestrierung mit LangChain oder LangGraph. - Betrieb produktionsnaher KI-Systeme: Monitoring (idealerweise Grafana), strukturiertes Logging, Fehleranalyse, Deployment. - Datenschutzkonforme KI-Gestaltung, gerade beim Umgang mit personenbezogenen Daten in Logging und Observability. - GenAI im Einsatz für viele Nutzer, idealerweise in einem Multimandanten-Umfeld. - Kubernetes, ArgoCD, Jenkins. - Erfahrung mit agilen Lieferstrukturen, idealerweise SAFe. - Erfahrung aus Projekten der öffentlichen Verwaltung. Benefits - Echte Produktivprojekte: KI, die beim Kunden in Betrieb geht. Kein Innovation-Lab, keine Folien. - Remote-first in der DACH-Region: Gelegentlich vor Ort, ansonsten arbeitest du von dort, wo du gut arbeitest. - Moderner KI-Stack: RAG, Agenten, Vektorsuche, MLOps. Aktueller Stack, kein Legacy-Ballast. - Internes Upskilling: Wir investieren in deine KI-Skills. - MacBook, außer der Kunde stellt eigene Hardware. - Flache Hierarchien: Die Gründer sind deine direkten Ansprechpartner. - Ein Team, das sich kennt, auch bei verteiltem Arbeiten.

Role Description We are seeking a Machine Learning Infrastructure Engineer to design, build, and operate high-performance, highly reliable inference platforms for serving large machine learning models in production. The role focuses on the systems engineering side of AI deployment, including: - Request routing - Batching - Caching - Autoscaling - GPU utilization - End-to-end observability across diverse model workloads The ideal candidate brings strong distributed systems and performance engineering expertise, has shipped serving systems at scale, and understands the trade-offs between latency, throughput, cost, and quality in ML serving. Qualifications - Bachelor’s or Master’s degree in Computer Science or a related field. - Six or more years of experience in distributed systems, infrastructure, or ML platform engineering. - Strong proficiency in Python and a systems language such as Go, Rust, or C++. - Deep experience operating high-throughput, low-latency services in production. - Hands-on experience with LLM or large model inference frameworks such as vLLM or TensorRT-LLM. - Strong understanding of GPU architecture, memory hierarchies, and accelerator utilization. - Familiarity with Kubernetes, autoscaling, and modern cloud platforms. - Experience with observability stacks including metrics, tracing, and structured logging. - Solid grounding in performance engineering and capacity planning. - Strong communication and incident response skills. Requirements - Design and operate model serving platforms supporting diverse workloads including LLMs, vision models, and recommendation systems. - Optimize inference performance using continuous batching, paged attention, speculative decoding, and request multiplexing. - Implement multi-tenant routing, rate limiting, and quality-of-service policies across model endpoints. - Build autoscaling and capacity management systems that balance latency, throughput, and cost. - Tune GPU utilization, memory management, and KV cache strategies for LLM serving workloads. - Integrate model serving with API gateways, identity systems, and observability platforms. - Implement caching, prompt deduplication, and response reuse strategies where appropriate. - Drive end-to-end observability including latency histograms, queue dynamics, GPU utilization, and error tracking. - Develop deployment workflows including canary releases, shadow testing, and automated rollback. - Operate incident response for high-availability AI services and drive durable reliability improvements. - Collaborate with ML and product teams to support new model releases and capability rollouts. - Implement security controls including request signing, content filtering, and abuse detection at the serving layer. - Document operational procedures, performance characteristics, and tuning guidance for internal teams. - Stay current with AI serving research and translate advances into production capabilities. Benefits - Competitive salary range: $100,000–$150,000 Annually - Full-time, Direct W2 position - 100% Remote work opportunity Company Description Bright Vision Technologies is a technology consulting and software development company delivering cloud, AI, data, and enterprise solutions across the United States. This is a fantastic opportunity to join an established and well-respected organization offering tremendous career growth potential.

• Collaborate with cross-functional partners (Product Managers, Data Scientists, Data Engineers, Software Engineers, Business teams) to build data and Machine Learning products • Take ownership of objectives and key results for your workstream, and own technical solutions in partnership with your manager • Architect and build robust systems to train, deploy, run inference, and monitor Machine Learning and AI systems at scale • Champion code quality, reusability, scalability, maintainability, and security, and provide input into strategic architecture decisions • Implement processes and tools to ensure data quality, enforce data governance policies and engineering best practices • Integrate Machine Learning and AI systems with production applications • Innovate with new approaches, staying abreast of current research and latest technologies in the broader ML engineering community

Role Description - Design and implement scalable data processing pipelines for ML training and validation - Build and maintain feature stores with support for both batch and real-time features - Develop data quality monitoring, validation, and testing frameworks - Create systems for dataset versioning, lineage tracking, and reproducibility - Implement automated data documentation and discovery tools - Design efficient data storage and access patterns for ML workloads - Partner with data scientists to optimize data preparation workflows Qualifications - 7+ years of software engineering experience, with 3+ years in data infrastructure - Strong expertise in GCP's data and ML infrastructure: - BigQuery for data warehousing - Dataflow for data processing - Cloud Storage for data lakes - Vertex AI Feature Store - Cloud Composer (managed Airflow) - Dataproc for Spark workloads - Deep expertise in data processing frameworks (Spark, Beam, Flink) - Experience with feature stores (Feast, Tecton) and data versioning tools - Proficiency in Python and SQL - Experience with data quality and testing frameworks - Knowledge of data pipeline orchestration (Airflow, Dagster) Requirements - Experience with streaming systems (Kafka, Kinesis) - Experience with GCP-specific security and IAM best practices - Knowledge of Cloud Logging and Cloud Monitoring for data pipelines - Familiarity with Cloud Build and Cloud Deploy for CI/CD - Experience with streaming systems (Pub/Sub, Dataflow) - Knowledge of ML metadata management systems - Familiarity with data governance and security requirements - Experience with dbt or similar data transformation tools