Machine Learning Engineer

Trudenty; London; Hybrid

Job description

Grow with us.

We are looking for a Machine Learning Engineer to work along the end-to-end ML lifecycle, alongside our existing Product & Engineering team.

About Trudenty:

The Trudenty Trust Network provides personalised consumer fraud risk intelligence for fraud prevention across the commerce and payments ecosystem, starting with first-party and APP fraud prevention.

We are at an exciting point in our journey, as we go to market and drive growth of The Trudenty Trust Network. This next chapter of our story is one in which we will drive impact across the commerce ecosystem, create to stay at the leading edge of innovation across the industry whilst building material value for our team (inclusive of shareholders).

We are a 10 person seed stage company that has secured partnerships with notable names in the payments and commerce ecosystem, and raised investment from our first choice of partners who align with our values and ambition for the future. Our team is one of exceptional ‘outliers’; defined by grit, resilience, creativity in problem solving, intelligence and mastery of our domains. We are also mission-driven and results-oriented. Working with us, you will get the opportunity to do some of the best work of your life and unfold your full potential as a human.

We are a remote team, that co-works from London frequently. So easy travel into London should be possible for everyone in our team.

The role

We are looking for a Machine Learning Engineer with a spike in data engineering and maintaining real-time data pipelines. You will work with our Product & Engineering team along the end-to-end algorithm lifecycle to advance the Trudenty Trust Network.

A bit more on what you’ll do:

Data Engineering

1. Develop and maintain real-time data pipelines for processing large-scale data
2. Ensure data quality and integrity in all stages of the data lifecycle
3. Develop and maintain ETL processes for data ingestion and processing

Algorithm Development, Model Training and Optimisation

1. Design, develop, and implement advanced machine learning algorithms for fraud prevention and user personalization
2. Train and fine-tune machine learning models using relevant datasets to achieve optimal performance
3. Implement strategies for continuous model improvement and optimization

Data Mining & Analysis

1. Apply data mining techniques such as clustering, classification, regression, and anomaly detection to discover patterns and trends in large datasets.
2. Analyze and preprocess large datasets to extract meaningful insights and features for model training

MLOps - Deployment into production environments, Monitoring and Maintenance

1. Experience deploying and maintaining large-scale ML inference pipelines into production
2. Implement and monitor model performance in production environments on Kubernetes and AWS cloud platforms.
3. Utilize Docker for containerization and orchestrate containerized applications using Kubernetes.

Code Review and Documentation

1. Conduct code reviews to ensure high-quality, scalable, and maintainable code
2. Create comprehensive documentation for developed algorithms and models

Collaboration

1. Collaborate with our cross-functional team; including the founders, sales, data scientists, engineers, and product to understand business requirements and implement effective solutions

Research and Innovation

1. Stay abreast of the latest advancements in fraud prevention and machine learning and contribute to the exploration and integration of innovative techniques

About you:

You will have proven experience with data science and a track record of implementing fraud prevention, credit scoring or personalization algorithms. Setting up and maintaining real data pipelines to feed your ML models is light work for you, and you would have been as comfortable if this JD was for a ‘data engineer’.

You have worked in a high growth and fast moving company. You are agile, comfortable with ambiguity and are a creative thinker who can apply research and past experiences to new problems.

What we’re looking for:

1. Education & Experience:
   1. Bachelor's or Master's degree in Computer Science, Data Science, or a related field.
   2. 5+ years of professional experience in a relevant area like fraud prevention or credit scoring
2. Machine Learning Expertise:
   1. Strong understanding of machine learning algorithms and their practical applications, particularly in fraud prevention and user personalization.
   2. Experience designing, developing, and implementing advanced machine learning models.
   3. Familiarity with machine learning frameworks such as TensorFlow, PyTorch, and scikit-learn.
3. Data Engineering Skills:
   1. Proficiency in developing and maintaining real-time data pipelines for processing large-scale data.
   2. Experience with ETL processes for data ingestion and processing.
   3. Proficiency in Python and SQL.
   4. Experience with big data technologies like Apache Hadoop and Apache Spark.
   5. Familiarity with real-time data processing frameworks such as Apache Kafka or Flink.
4. MLOps & Deployment:
   1. Experience deploying and maintaining large-scale ML inference pipelines into production environments.
   2. Proficiency with Docker for containerization and Kubernetes for orchestration.
   3. Familiarity with AWS cloud platform (experience with GCP or Azure is a plus).
   4. Experience monitoring and optimizing model performance in production settings.
5. Programming Languages:
   1. Strong coding skills in Python and SQL.
   2. Experience with Node.js, JavaScript (JS), and TypeScript (TS) is a plus.
6. Statistical Knowledge:
   1. Solid understanding of statistical concepts and methodologies for analyzing and interpreting large datasets.
   2. Ability to apply statistical techniques to validate models and algorithms.
7. Data Manipulation & Analysis:
   1. Proficient in data manipulation and analysis using tools like Pandas, NumPy, and Jupyter Notebooks.
   2. Experience with data visualization tools such as Matplotlib, Seaborn, or Tableau to communicate insights effectively.

Our offer:

1. Cash: Depends on experience
2. Equity: Generous equity package, on a standard vesting schedule
3. Impact & Exposure: Work at the leading edge of innovation building our machine-learning powered smart contracts for fraud prevention
4. Growth: An opportunity to wear many hats, and grow into a role you can inform
5. Hybrid work: Flexibility to work from home, with travel into London

The process:

1. Submit your CV along with answers to the handful of questions we ask of every candidate
2. A 60min call to explore initial fit with the founders
3. A 60min technical problem solving interview, alongside your potential ML colleague
4. Final discussion with the Founder CEO to align before we make a formal offer