Staff Machine Learning Engineer

What you will be doing:

We are looking for a great staff engineer to help evolve our cutting edge machine learning based anti-money laundering solution that our clients use to stop money ending up in the hands of bad actors. You will work within a squad focussed on the extraction of entities, risks and relationships from millions of sources across the web. 

As a Staff Machine Learning Engineer you will shape our ways of working with machine learning, and help evolve a financial crime knowledge graph that spans public and private data, that in turn is helping our customers make financial crime a thing of the past.

You will build, deploy and manage in house machine learning models, community and commercial large language models and related prompting strategies, as well as related ML ops processes and data pipelines. As a staff engineer you will also collaborate with and mentor ML engineers in other squads in the tribe to support the ongoing expansion and quality improvements of our financial crime knowledge graph.

Scope of the role:

All Staff level engineers at ComplyAdvantage work within squads but are also expected to foster collaboration across the squads in a tribe. As a Staff Machine Learning engineer you will specifically need to have deep technical expertise in the domain of machine learning, both aspects of this role are described next.

Scope of Staff Engineers at ComplyAdvantage:

• Sets medium-term technical direction for the tribe and team in collaboration with peers and engineering leads
• Proactively identifies tribe-level opportunities and issues, proposes appropriate solutions and influences tribe level technology goals
• Leads inter-disciplinary and cross-team projects with hands on involvement where required
• Proactively works to align work across multiple teams and tribes to maximise the impact of any delivered features
• Help engineers make design decisions that minimise the cost of future changes and reduce dependencies between teams and services. 
• Performs technical interviews and mentors other engineers to do the same
• Acts as the leading expert at one or more technical and business domains in the company

Our Tech Stack:

• Our technology stack is designed to run on public cloud architectures, notably AWS and GCP. 
• Development is organised around Kotlin and Python for our backend languages and TypeScript with React for our frontend stack. 
• We make substantial use of relational database technologies, notably Postgres, and also use of  a distributed SQL database as Yugabyte
• We also use an event-sourced model powered by Kafka for our communication bus and gRPC for our intra-service communication protocol. 
• For our data and AI teams, experience in machine learning development and very large-scale columnar data stores (e.g. Apache HBase, Databricks) is key, as well as experience with large-scale data streaming technologies such as Apache Spark, graph databases (e.g. Neo4j, AWS Neptune, TigerGraph)
• We use modern observability solutions built on Grafana Cloud, and deploy our code using ArgoCD

We have a strong emphasis on engineering excellence and strive to ship the best possible code and the best possible solutions to our customers.

About you:

Machine learning and engineering skills required of the role:

• Build/train and productionize machine learning models for your squad
• Collaborate with the SRE team to build out and maintain the ML platform for your squad
• Build capabilities to monitor model performance and feature drift
• Where appropriate re-use public models and techniques such as prompt engineering and RAG to reduce time to value
• Collaborate with other software engineers in a cross functional team to design and implement intelligent services
• Design software with scale, transparency and ease of operation in mind, writing maintainable, performant and well-tested code in Python
• Mentor other machine learning engineers
• Integrate ML models into new and existing data pipelines to drive positive impacts for CA’s customers, including feature engineering as well as building APIs and consuming and producing event streams as inputs and outputs of models
• Undertake prototyping and research work in collaboration with data scientists to determine the best approach to achieve the team’s goals

As a Staff Machine Learning Engineer in the Customer Risk Squad:

• While we have very mature ML and LLM based agent chains in other squads our customer risk squad has just started adding AI to this part of the product
• As such you will have a fantastic opportunity to build a number of new AI features and models from the ground up, such as:
• An LLM based conversational agent that allows users to describe what risks they care about and automatically configures our back end risk models
• A custom model or agent chain that learns from our customers past risk remediations to produce risks scores to be used instead of or as a compliment to a rules based risk model

Education: 

• BSc/BA degree in computer science, engineering or related discipline OR relevant years of experience in required skills.

Nice to haves:

• Experience working with cloud (AWS / Azure / GCP) or containerised infrastructure (Kubernetes / Docker / ArgoCD / Argo Workflow
• Experience with databases, event brokers (Kafka) or message queues, and data engineering workflows (batch processing, ETL, streaming)

What’s in it for you? 

• Equity as we want you to have a part of what we are building 
• Private medical insurance designed to keep you ensuring peace of mind while you excel in your career
• Unlimited Time Off Policy - A work-life balance and focus on our well-being are critical to keeping us performing at our best 
• We embrace a hybrid approach that requires employees to be in the office for two days a week. We strongly believe that this approach fosters collaboration and enables the building of meaningful relationships
• You will also get a new starter budget to kit out your home office 
• Opportunity to work on innovative projects with smart-minded people keen to share their knowledge and continuously improve 
• Annual learning budget (prorated based on start date) to drive your performance and career development