Senior AI/ML Engineer - Remote | Romania or Malta

Besedo; United States; A distancia; USD 120.000 - 180.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Remote work

Descripción de la vacante

Besedo is seeking a senior AI/ML professional to lead productionization and continuous optimization of ML systems for Implio across remote teams or offices in the region. The role emphasizes production-ready ML, observability, and cost-performance trade-offs.

You will own training pipelines, inference services, deployment patterns, and release workflows, collaborating with DevOps and software engineers to deliver reliable and scalable ML solutions.

Formación

• Master’s, PhD, or equivalent in CS/Engineering/Data Science with strong math/stat ML foundations.
• 6+ years in ML engineering and MLOps with production delivery track record.
• Experience deploying models to production with scalable serving and reliable rollouts.
• Expertise in model performance optimization: latency, batching, quantization, ONNX/TensorRT.
• Strong Python proficiency with PyTorch, scikit-learn, ONNX, TensorRT.
• CI/CD for ML (GitLab CI), Docker, reproducible ML workflows.
• Nice to have: Kubernetes, AWS, FastAPI, SageMaker, feature stores.

Responsabilidades

• Handle the production lifecycle of ML systems: training, packaging, deployment, monitoring.
• Design, build, and improve training/retraining pipelines.
• Build high-performance inference services and deployment patterns.
• Drive inference optimization for latency and cost improvements.
• Partner with DevOps/SRE for scalability, reliability and observability.
• Own model versioning, CI/CD, and release workflows for reproducibility.
• Strengthen data & model monitoring with feedback loops.
• Communicate results and trade-offs to stakeholders.
• Ensure model quality through rigorous evaluation and validation.

Conocimientos

Python

PyTorch

scikit-learn

ONNX/TensorRT

CI/CD for ML

Docker

Kubernetes

AWS

Monitoring & observability

Educación

Master’s/PhD in CS/Engineering/Data Science

Herramientas

Docker

Kubernetes

AWS

SageMaker

FastAPI

Descripción del empleo

Location: Malta; Romania

Who are we

Besedo is a tech company delivering Trust & Safety solutions to online marketplaces worldwide. Every year, we review and moderate over 500 million pieces of user-generated content and block more than 40 million fraud attempts – helping online platforms stay safe and trusted for millions of users.
Besedo has headquarters in Stockholm (Sweden)and employs over 300 employees in 5 offices in different countries. Implio is our all-in-one SaaS moderation platform that combines state-of-the-art AI (deep learning, NLP, computer vision) with a powerful user interface for human moderation and powerful analytics. The result is an easy-to-use content moderation solution that enables companies to reduce risks, protect their users and build safer online environments.

Learn more about Implio in thisvideo, and discover more about Besedo on ourwebsite.

About the role

We are looking for a senior-level AI/ML professional to lead the productionization, deployment, and continuous optimization of ML systems in mission-critical environments. This role requires strong technical leadership, deep hands-on experience shipping models to production, and the ability to drive reliability, scalability, and cost/performance trade-offs end-to-end. The ideal candidate combines strong ML depth with MLOps and production engineering excellence, and can operate autonomously while influencing architecture and best practices across teams.

Key Qualifications

• Master’s, PhD, or equivalent experiencein Computer Science, Engineering, Data Science (or related), with strong foundations in mathematics, statistics, and ML.

• 6+ years(or equivalent) experience across ML engineering and MLOps / production ML, with a proven track record deliveringhigh-impact systems in production.

• Demonstrated expertise deploying models to production: scalable serving patterns, model packaging, inference optimization, observability, and safe rollout strategies.

• Strong experience withmodel performance and efficiency optimization: latency/throughput tuning, batching, quantization, ONNX/TensorRT, GPU/CPU optimization, memory and cost tuning.

• Strong proficiency inPython.

• Hands-on experience with ML frameworks such asPyTorch, scikit-learn, and optimization/runtime stacks likeONNX, TensorRT.

• Strong grasp ofCI/CD for ML(e.g., GitLab CI), containerization (Docker), and reproducible workflows.

• Experience withmonitoring and reliability: metrics/logging/tracing, model/data drift, alerting, SLOs, incident response practices.

• Plus (nice to have):Kubernetes, AWS, FastAPI (and/or similar Python serving frameworks), SageMaker, service meshes, feature stores, model registries.

What will you own

• Handle the production lifecycleof ML systems: training, packaging, deployment, monitoring and controlled rollouts.

• Design, build, and continuously improvetraining and retraining pipelines(data ingestion, labeling/QA loops, feature generation, experiment tracking, reproducibility).

• Build and improvehigh-performance inference servicesand deployment patterns.

• Driveinference optimization(ONNX/TensorRT, quantization, batching, GPU/CPU tuning) with measurable latency/cost improvements.

• Partner with DevOps/SRE to ensureoperational excellence: scaling, reliability, incident readiness, observability, and alerting.

• Ownmodel versioning, CI/CD, and release workflowsensuring reproducibility and safe delivery to production.

• Strengthendata & model monitoring(performance, drift, quality) and implement feedback loops for continuous improvement.

• Communicate results and trade-offs to stakeholders, turning technical outcomes into business value.

• Ensure model quality through rigorous evaluation and production-grade validation aligned with evolving data and business needs.

How you will work
This is a 100% remote role. To be considered, you must be based in, and have the right to work in Romania or Malta.

* You will work with a team of talented Machine Learning Engineers, DevOps and Developers who are passionate about their work and like to have fun in the process.

We welcome applicants of all backgrounds.

What it’s like working with us?

At Besedo, we all come from different cultures and backgrounds, but we share a common set of values:

• We like to get things done

• We support each other to reach our goals and grow as professionals

• We love to learn, share and have fun together