Leega is a company focused on delivering efficient and innovative service to its clients. This commitment is no different when it comes to our primary fuel: people! Our culture is inspiring, and our values are embedded in everyday actions: ethics and transparency, quality excellence, teamwork, economic, social and environmental responsibility, human relationships, and credibility. We seek innovative professionals who are driven by challenges and focused on results. If you are looking for a dynamic, collaborative company that invests in its employees through continuous training, Leega is the place for you! **>> LEEGA IS FOR EVERYONE — we would be thrilled to welcome you to our team. Join us in shaping our story and building our future.** Apply now to our open positions! **Responsibilities and Duties** **About the Opportunity** You are the bridge connecting prototypes to production. You will design and build the ML engineering infrastructure for our pricing engine — including inference serving, training pipelines, and feature engineering — enabling complex models to run in real time with low latency on Ray. Your focus is on ML modeling and coding; the platform and runtime are managed by the MLOps/Platform team, with whom you collaborate closely. **Your Challenges** * **Inference Serving —** Design chained model pipelines on Ray Serve — model composition, low-latency serving, and update strategies. * **Distributed Training —** Build training pipelines (Ray Train/Data), hyperparameter optimization (Ray Tune), and tenant-specific trained models with resilient checkpointing. * **Feature Engineering —** Define and materialize features in the feature store (Feast/Redis), ensuring consistency between training and production. * **Optimization and RL —** Implement and optimize pipeline components for optimization (linear programming) and offline RL in the pricing pipeline. * **Model Quality —** Monitor modeling-related drift, validate model versions, and generate explainability (SHAP) — in partnership with MLOps. * **Technical Leadership —** Serve as a technical reference, mentor team members, and jointly define what is feasible and scalable with the team. *You hand off work to data scientists, receive data from data engineers, and deliver outputs to the MLOps/Platform team for deployment and operations.* **Requirements and Qualifications** **Stack & Tools** * **ML Serving & Training:** Ray (Serve, Train, Tune, Data, RLlib) * **Registry & Features:** MLflow, Feast + Redis * **Optimization:** Linear programming (Gurobi, HiGHS), offline RL * **Language & Runtime:** Python; Docker; Iceberg reading **What We’re Looking For** **Essential** * Proven experience deploying ML models into production. * Proficiency in Python and strong foundational software engineering skills (APIs, testing, clean code). * Experience with inference serving and low-latency optimization. * Familiarity with containers (Docker) and MLOps workflows (model registry, deployment). * Comfort with AI-assisted development (Claude Code). **Nice-to-Have** * Deep expertise in the Ray ecosystem (Serve, Train, Tune, RLlib) — a strong differentiator. * Feature stores (Feast) and large-scale, low-latency serving using Redis. * Optimization/solvers (Gurobi, HiGHS) or real-time revenue management; offline RL. * Generative AI serving (vLLM, LiteLLM) and multi-tenant architectures. **Additional Information** * **Remote Work** * **Project Duration:** 6 months, with potential extension or internalization. At Leega, we don’t just deliver lines of code or dashboards. We transform complex technological challenges into tangible impact. With over 15 years of experience, we combine deep human expertise with the speed of Artificial Intelligence to build solutions that transform businesses — and, above all, improve people’s lives. We are a technology consulting firm — agnostic and strategic. With offices in Brazil and Europe, our team of over 580 multidisciplinary talents lives and breathes the Data Analytics, Cloud, and AI ecosystem. We master the full foundation — from Governance to Engineering — ensuring technology is not just a tool, but a sustainable competitive advantage for the world’s leading enterprises.
João Silva
Indeed · HR
João Silva
Indeed · HR
