Tevos M.
Machine Learning Engineer
One of his most notable achievements is the architecture and production-scale deployment of a consumer-facing real-time ML pipeline at Philip Morris International (PMI). This project demonstrated not only his deep technical expertise but also his leadership in driving innovation, ensuring business impact, and successfully operationalizing machine learning in a high-stakes environment.
Tevos is highly skilled at translating complex business and technical challenges into scalable, production-ready ML systems. He also plays a key role in mentoring engineering teams and shaping technical strategy, making him a strong leader in the machine learning space.
Main expertise
Python6 years
FastAPI3 years
Apache Spark3 years
Docker5 yearsExperience7
Machine Learning Engineer
- Joined as a Machine Learning Engineer and was later promoted to Technical Lead to guide the team through key transitions.
- Led multiple ML projects from proof-of-concept (POC) to minimum viable product (MVP), ensuring scalability and production readiness.
- Transformed the ML infrastructure into a cloud-agnostic stack, optimizing flexibility and cost-efficiency.
- Architected and managed the development of two Agentic bots, including Retrieval-Augmented Generation (RAG) components.
- Oversaw the implementation of a recommendation system and a voice classification model, ensuring robust performance and alignment with business goals.
- Established MLOps practices, including CI/CD pipelines, monitoring, and alerting systems to support maintainability and automation.
- Facilitated cross-functional collaboration, aligning data science, engineering, and product teams.
Machine Learning Technical Lead
-
Initially joined as a Machine Learning Engineer, then elected as the Technical Lead to guide the team through key transitions;
-
Led the evolution of multiple ML projects from proof-of-concept (POC) to minimum viable product (MVP), ensuring scalability and production-readiness;
-
Spearheaded the transformation of the ML infrastructure into a cloud-agnostic stack, optimizing for flexibility and cost-efficiency;
-
Architected and managed the development of two Agentic bots, including Retrieval-Augmented Generation (RAG) components;
-
Oversaw the implementation of a recommendation system and a voice classification model, ensuring robust performance and alignment with business goals;
-
Established MLOps practices, including CI/CD pipelines, monitoring, and alerting systems to support long-term maintainability and automation;
-
Facilitated cross-functional collaboration, driving alignment between data science, engineering, and product teams;
-
Mentored junior engineers and fostered a culture of technical excellence and knowledge sharing within the team.
MongoDBDocker
AWS
RedisPython
Machine Learning Engineer
- Set up backend CI/CD processes for existing computer vision auto-scaled deep learning model pipelines.
- Developed a new deep learning model to enhance operational functionality within the analytics stack.
- Implemented a CI/CD workflow that enabled fast and safe updates across the full ML lifecycle, critical during the agricultural season.
- Optimized processes to reduce costs and latency while maintaining accuracy metrics.
Machine Learning Operations Engineer
-
Set up the backend CI/CD processes for existing computer vision auto-scaled DL model pipelines;
-
Developed a new DL model to enhance operational functionality within the analytics stack;
-
Implemented a CI/CD process enabling fast and safe introduction of changes in the full ML lifecycle, critical during the agricultural season;
-
Optimized processes to achieve cost and latency reduction while maintaining accuracy metrics.
Docker
Jenkins
OpenCV
PyTorch
Senior Data Scientist / MLOps
- Maintained and expanded an end-to-end consumer-facing real-time ML pipeline in production.
- Architected and developed the initial pipeline, ensuring robust and scalable infrastructure.
- Conducted ad-hoc projects focused on data mining and mathematical modeling.
- Classified items early in the product lifecycle, significantly reducing service and logistics costs.
- Laid the foundations for a second version of the pipeline to enable predictive maintenance.
DockerApache Spark
FlaskJenkins
Kubernetes
Machine Learning Engineer
- Developed and applied key financial ratios and quantitative models to evaluate market-related parameters, including Value at Risk (VaR), ensuring accurate risk forecasting and exposure analysis.
- Conducted in-depth technical analysis of structured finance instruments, such as mortgage-backed securities (MBS) and collateralized debt obligations (CDOs), using stress testing, scenario modeling, and sensitivity analysis to assess performance under varying market conditions.
- Designed and refined risk assessment methodologies, combining traditional financial theory with data-driven techniques to enhance decision-making and portfolio resilience.
- Collaborated with risk management and investment teams to translate complex analytical insights into actionable recommendations.
- Automated risk reporting pipelines and dashboards, improving transparency and accelerating response to market fluctuations.
- Evaluated regulatory compliance of risk models, ensuring adherence to internal risk frameworks and external standards such as Basel III and IFRS.
- Contributed to model validation by backtesting performance metrics and calibrating models for improved accuracy and robustness.
SQL
Scikit-learn
Machine LearningFinancial Analyst / Data Analyst
-
Developed and contributed to packages dedicated to data ETL, ML, and statistical analysis;
-
Enhanced general operation components of the stack, including GUI-related elements, for team projects;
-
Worked on structured and unstructured knowledge extraction and NLP tools.
Machine LearningAssessments
Engineering excellence
Tevos’s overall performance in a 90-minute live technical assessment ranks in the top 10% of vetted Machine Learning Engineers at Proxify.
Education
Stop browsing.
Get matched faster.
Talk to an expert and get tailored matches from our network in just 2 days.
A network of over 6,000+ tech experts
Get matched with perfect-fit talent in 2 days on average
Hire quickly and easily with 94% match success