Senior Applied ML Engineer | Kimchi (Model Router)
Cast AIÖsterreich · Remote
Every request gets a decision: which model serves it.
Entwicklung & ResearchVollzeit
Large Language ModelsMachine LearningPyTorchAgentic AIOpenAI
vor 2 Wochen
536 geprüfte KI-Jobs
Wie wir sortierenJunior Data Scientist
SeedtagDüsseldorf · Remote
We’re looking for a Junior Data Scientist to join our tech team and help build the future of neuro-contextual advertising at global scale.
Entwicklung & ResearchVollzeit
Data ScienceLarge Language ModelsLangGraphMachine LearningComputer Vision
vor 2 Wochen
Machine Learning Engineer (m/f/d) VLA Training & Evaluation
Agile RobotsMünchen
The AI Teams at Agile Robots are looking for a Machine Learning Engineer (m/f/d) VLA Training & Evaluation, who will build the frameworks fo
Entwicklung & ResearchVollzeit
Machine LearningDeep LearningPyTorchFine-TuningTransformer
vor 2 Wochen
Lead Solutions Architect - Generative AI (EMEA Emerging DNB)
DatabricksDeutschland
We are looking for a Lead Solution Architect focused on Generative AI to support our EMEA Emerging Digital Natives and Startups business uni
IntegrationVollzeit
Generative AILarge Language ModelsRAGMachine LearningDeep Learning
vor 2 Wochen
Senior ML Engineer (Agentic Search)
NebiusDeutschland
Train and deploy ML models for retrieval, reranking, and search relevance, such as embedding models and cross-encoders, in production - Deve
IntegrationVollzeit
Agentic AILarge Language ModelsMachine LearningDeep LearningHugging Face
vor 2 Wochen
Neue Jobs per E-Mail
Wir schreiben dir, sobald eine neue geprüfte Stelle dazukommt. Höchstens eine Nachricht am Tag, und nur, wenn es tatsächlich etwas Neues gibt.
Abmelden mit einem Klick, jederzeit. Keine Weitergabe an Dritte.
MLOps Engineer (m/f/d)
Redcare PharmacyKöln
About : We are seeking a MLOps Engineer (m/f/d) to build, operate, and improve ML/AI solutions in production.
Infrastruktur & MLOpsVollzeit
MLOpsData ScienceMLflowKubeflowMachine Learning
vor 2 Wochen
Senior Agentic Platform Engineer
SeedtagDüsseldorf · Remote
We’re looking for a Senior Agentic Platform Engineer to join our tech team and help build the future of neuro-contextual advertising at global scale.
Infrastruktur & MLOpsVollzeit
Agentic AILarge Language ModelsLangGraphLLMOpsComputer Vision
vor 2 Wochen
MLops Engineer
SeedtagHamburg · Remote
We’re looking for an MLOps Engineer to join our tech team and help build the future of neuro-contextual advertising at global scale.
Infrastruktur & MLOpsVollzeit
MLOpsMachine LearningComputer VisionAgentic AIMLflow
vor 2 Wochen
AI LLM Architect - Manufacturing and Operations (All Genders)
AccentureWürzburg
Your Mission At Accenture, you shape the environment in which you thrive – with ways of working that suit you.
Entwicklung & ResearchVollzeit
Large Language ModelsRAGMachine LearningDeep LearningGenerative AI
vor 2 Wochen
Senior AI-Native Data Engineer (f/m/x)
ExmoxHamburg · Remote
Your Mission This is a company built for growth.
Infrastruktur & MLOpsVollzeit
Agentic AIDatabricksMachine LearningClaudePrompt Engineering
vor 2 Wochen
Senior AI Data Expert (f/m/x)
ExmoxHamburg · Remote
Your Mission This is a company built for growth.
Entwicklung & ResearchVollzeit
Machine LearningAgentic AIData ScienceDatabricksClaude
vor 2 Wochen
Senior Software Engineer - Machine Learning (all genders)
ZalandoBerlin
The Lounge Assortment Optimisation team builds the decision products behind a better assortment and customer experience.
Infrastruktur & MLOpsVollzeit
Machine LearningLarge Language ModelsMLOpsGenerative AIDatabricks
vor 2 Wochen
AI/ML Senior Engineer Embedded AI (f/m/d)
AptivDeutschland
Leitet die Entwicklung von KI-Algorithmen für Embedded-Systeme, benchmarkt und optimiert sie für Echtzeit auf Beschleuniger-Hardware und wählt AI-SoCs aus.
Entwicklung & ResearchVollzeit
Deep LearningMachine LearningEmbedded AIC/C++Transformer-Modelle
vor 2 Wochen
Machine Learning Engineering Manager
DeepLMünchen
As Engineering Manager for the Production Inference team, you will own both people leadership and technical direction for a team of research
Entwicklung & ResearchVollzeit
Machine LearningLarge Language Models
vor 2 Wochen
Senior Software Engineer
SeedtagDüsseldorf · Remote
We’re looking for a Senior Software Engineer to join our tech team and help build the future of neuro-contextual advertising at global scale.
Entwicklung & ResearchVollzeit
Large Language ModelsRAGMachine LearningComputer VisionData Science
vor 2 Wochen
Engineer, Field Applications
Analog DevicesMünchen
Join a technical team developing intelligent systems that connect the physical and digital worlds.
Entwicklung & ResearchVollzeit
Machine LearningPyTorchTensorFlowComputer VisionCUDA
vor 2 Wochen
Senior Data Scientist (f/d/m)
Digital Charging SolutionsBerlin
Make an Impact by: In this role, you will develop models and insights that help predict charging behavior, optimize billing, and improve customer engagement.
Entwicklung & ResearchVollzeit
Data ScienceMachine LearningLarge Language Models
vor 2 Wochen
Staff Machine Learning Engineer, LLM Inference Optimization
NebiusBerlin
Own a platform-level optimization pillar such as quantization, speculative decoding, KV-cache optimization, engine selection, or long-context serving.
Entwicklung & ResearchVollzeit
Large Language ModelsMachine LearningPyTorchAgentic AITransformer
vor 2 Wochen
Technical Curriculum Developer, Platform - EMEA
ClickHouseDeutschland
Betreibt die Infrastruktur für Kurse und Zertifizierungen und baut GenAI-Workflows sowie KI-Agenten für Content-Erstellung und Lernende.
Entwicklung & ResearchVollzeit
Machine LearningGenerative AIPrompt EngineeringContent as CodeCI/CD
vor 2 Wochen
Head of Data Intelligence & AI (m/w/d)
Storymachine GmbHBerlin
KI-Offensive und Automatisierung: ➡️ Du treibst unsere interne KI-Offensive strategisch und operativ voran, ➡️ Du integrierst LLMs in Analys
Anwendung & Creation
Large Language ModelsData ScienceKI-Tools
vor 2 Wochen
Computational Scientist / Scientific Machine Learning
FusionalityLausanne
Fusionality is building the measurement, simulation, and control stack for the fusion energy reactors of the future.
Entwicklung & Research
Machine LearningPyTorchAgentic AI
vor 2 Wochen
Cloud Engineer AI Workplace (w/m/d)
KfW BankengruppeBerlin
Die KfW nutzt Cloud-Technologien, um Anwendungen mit Künstlicher Intelligenz umzusetzen.
Infrastruktur & MLOpsVollzeit
Machine LearningMLOpsAgentic AIData ScienceAzure AI
vor 2 Wochen
Cloud Engineer AI Workplace (w/m/d)
KfW BankengruppeFrankfurt am Main
Die KfW nutzt Cloud-Technologien, um Anwendungen mit Künstlicher Intelligenz umzusetzen.
Infrastruktur & MLOpsVollzeit
Machine LearningMLOpsAgentic AIData ScienceAzure AI
vor 2 Wochen
Lab Coordinator BioNMR Facility & Data Science Specialist
Universität WienWien
Betreut die BioNMR-Anlage, schult Nutzer, baut Python/R-Datenpipelines und integriert ML-Werkzeuge in die Spektrenverarbeitung.
Entwicklung & Research3.443 bis 3.443 € / MonatTeilzeit
Data ScienceMachine LearningNMR-SpektroskopieGerätebetreuung und TroubleshootingNutzerschulung
vor 2 Wochen
Machine Learning Engineer
StreamUnlimited Engineering GmbHWien
As an Edge AI ML Engineer, you will develop, optimize, and deploy machine learning models for audio and multimodal intelligence on real devices.
Entwicklung & Research
Machine LearningDeep LearningEdge AI
vor 2 Wochen
Senior Applied ML Engineer | Kimchi (Model Router)
Cast AIÖsterreich · Remote
Zur OriginalanzeigeDie Bewerbung läuft direkt beim Arbeitgeber.
Warum dieser Job gelistet ist
Eindeutige KI-Rollenbezeichnung im Stellentitel. Prüfverfahren ansehen
Aufgaben
Every request gets a decision: which model serves it. This is an applied-ML seat, not an infrastructure one. Platform engineers own the proxy, the streaming path, and the fleet.
You own the model inside them: the training data, the objective, the evaluation, and the iteration loop that ships a better router every cycle. The problem: routing is a prediction problem wearing a product s clothes. For every request you predict the quality each candidate model would deliver, what it would cost, and how fast it would decode, and you have to be right enough, in aggregate, that the savings are real and the quality never dips below frontier.
The data is messy: rollout outcomes from benchmark harnesses, per-request records from the live fleet, override signals, and token streams whose speed depends on the serving concurrency at the moment. Speed itself is a correctness variable: on deadline-bound agentic work, a model that decodes three times slower doesn t do the same work slower, it does less work. That s why naive cost-per-token objectives quietly optimize for the wrong thing.
And the bar for evidence is high: a router change ships only after production-parity evaluation with error bars, then gets held to its numbers in live traffic. Stack: Python; PyTorch; SQL at scale (ClickHouse); OpenAI- and Anthropic-compatible LLM APIs; benchmark and rollout harnesses (RouterBench-class); GitLab CI.
Anforderungen
You ve spent 5+ years in applied ML or ML research, and you ve trained, evaluated, and shipped models that make real-time decisions (ranking, recommendation, bandits, pricing, or LLM routing) and you can tell that story with receipts. - Strong Python and SQL at scale: you can pull, clean, and interrogate millions of request-level records without waiting on anyone. - You know the difference between a model that got better and an eval that got easier. - You have real opinions about what LLM benchmarks measure, agentic harnesses included. - You know enough serving reality (TTFT, decode speed, batching, prefix caching, concurrency) to model the objective honestly. - You instrument before you optimize, error bars and all. - A wide mandate excites you more than it unsettles you. Nice to haves - You ve worked on LLM routing specifically: RouterBench-class evals, costlatency Pareto fronts. - Calibration, abstention, or conformal methods in production decision systems. - You ve run online A/B loops with drift monitoring on a model that touches real money. Responsibilities - Own the routing model end to end: features, objective, training, calibration, and release cadence.
Iterate it like a product, not a research artifact. - Build the evaluation that gates every change: production-parity benchmarks, router-vs-router comparisons, holdouts by task family, error bars on pass rates. Nothing ships on vibes. - Turn fleet data into training signal: per-request outcomes from production, benchmark rollouts, and override feedback, with failure categorization (infra vs task) so poisoned labels never reach the policy. - Model the objective the user actually experiences: task success × token cost × wall-clock speed under the real concurrency regime, with cached-input economics in the picture. - Run the online loop: shadow, A/B, full rollout, drift monitoring, retrain. When production disagrees with your offline eval, you find out why before the next ship. - Push the frontier where it pays: calibrated decisions, abstention under uncertainty, speed-aware routing.
We experiment on what a router should be, not just which model it picks today. - Partner with platform engineers on instrumentation: the features and labels recorded per request (decode speed first-class among them) and the experiments the data path must support. What’s in it for you? - Competitive salary (depending on the level of experience). - Enjoy a flexible, remote-first global environment. - Collaborate with a global team of cloud experts and innovators, passionate about pushing the boundaries of Kubernetes technology - Equity options. - Get quick feedback with a fast-paced workflow. Most feature projects are completed in 1 to 4 weeks. - Spend 10% of your work time on personal projects or self-improvement. - Learning budget for professional and personal development - including access to international conferences and courses that elevate your skills. - Annual hackathon to spark new ideas and strengthen team bonds. - Team-building budget and company events to connect with your colleagues. - Equipment budget to ensure you have everything you need. - Extra days off to help maintain a healthy work-life balance.
Hiring process - Screening call with Recruiter - Hiring Manager interview - Technical interview (system design) - Live coding - Culture Check interview with an executive As part of our standard hiring process, we would like to inform you that a background check may be conducted at the final stage of recruitment through our third-party provider, Checkr. Please note that Cast AI does not provide any form of visa sponsorship/work permit. #LI-Remote
Zur Position
Why Kimchi? Great models are raw ingredients. Kimchi is what happens when you ferment them with good engineering.
We started inside CAST AI helping companies run LLMs on their own Kubernetes clusters; today we run our own coding harness on any model you pick, and the router deciding which model answers each request is ours too. The Auto Router Our promise is one enforcement layer for your AI: budgets, spend attribution, and model routing, applied before a request ever hits a model. The Auto Router makes the call: for every request, which model serves it.
Eight open-source models whose input prices span more than 20×, cached input up to 50× cheaper than fresh, frontier providers on customers own keys, and a coding agent that fires hundreds of requests before its task is done. Frontier-level task success at a fraction of the token cost: that sentence is the product, and it stays true only if the model inside the router keeps getting better. That model is yours.
Made by Cast AI — a Miami-headquartered, globally distributed team across 34 countries that hit unicorn status in January 2026 with a $50B+ backed investment pushing its valuation past $1 billion. About
Interesse an dieser Position?
Die vollständige Anzeige und das Bewerbungsformular liegen beim Arbeitgeber.
Zur Originalanzeige