Senior ML Engineer, Doc Fraud

Join us at Entrust At Entrust, we’re shaping the future of identity centric security solutions. From our comprehensive portfolio of solutions to our flexible, global workplace, we empower careers, foster collaboration, and build solutions that help keep the world moving safely . Get to Know Us Headquartered in Minnesota, Entrust is an industry leader in identity-centric security solutions, serving over 150 countries with cutting-edge , scalable technologies. But our secret weapon? Our people. It’s the curiosity , dedication, and innovation that drive our success and help us anticipate the future. Senior ML Engineer - Document Extraction Entrust (Identity Verification) Locations: - London (Hybrid, 3 days onsite) - Portugal (Hybrid or Remote) Department: Engineering Reports To: Engineering Manager Job Type: Full-Time The role We're looking for a Senior Software Engineer to join our Document Fraud team, where you'll build products that delight customers across all our product offerings including: financial services, driving verification, proof of address, and much more. Our team builds the fraud detection capabilities that power identity, processing government identity documents to enable secure document verification, fraud prevention, and seamless customer onboarding experiences. As a Senior Software Engineer on the Document Extraction team, you'll focus on delivering high-accuracy extraction with global document coverage. You'll contribute to our Document Verification offering, helping customers create smooth and secure onboarding experiences. To achieve this, you'll leverage cutting-edge technology including VLM/LLMs and traditional ML approaches in production systems at scale, tackling challenges from designing training and evaluation pipelines, optimising inference for real-time extraction, and integrating as part of our product offering. The job is done when we have happy customers reaping the benefits of what modern technology allows us to do. What You'll Do Work closely with Applied Science, Product, Design, Data Science, and Operations to deliver highly accurate and performant document classification and extraction solutions across thousands of documents globally. Lead the technical design of complex features and systems, taking ownership from RFC through implementation to production deployment. You'll produce clean, well-reasoned designs that leverage your experience to avoid pitfalls and age well over time. Build and optimize production ML systems that matter: develop repeatable pipelines for training, evaluating, and deploying LLM models; implement GPU optimizations for inference; design advanced labeling workflows to improve model accuracy; and engineer robust solutions that deliver measurable customer value through faster processing and more accurate extraction. Champion performance, scalability, and reliability by deeply understanding how our systems operate in production. You'll identify and tackle technical debt proactively, scope and stage releases effectively to ensure smooth deployments, and build metrics into features to measure success empirically. Drive technical excellence across the team by leading RFCs, reviewing critical code, holding peers accountable for quality (code review, testing, documentation), and making well-reasoned tradeoffs between competing priorities. You'll work with Product to prioritize features and ensure the team delivers on its commitments. Mentor and enable other engineers through pair programming, technical guidance, and collaborative problem-solving. You'll help team members deliver quality code, navigate complex challenges, and grow their skills. Coordinate solutions to cross-cutting technical problems, working seamlessly across team and organizational boundaries. You'll overcome roadblocks respectfully and constructively, ensuring dependencies are tracked and issues have clear owners. Contribute to a culture of continuous improvement, psychological safety, and collaboration through active participation in our squad-based organization, retrospectives, written documentation (RFCs, DACIs), and cross-functional partnerships. What We're Looking For Strong production engineering experience: You've built, deployed, and operated complex systems in production. You understand observability, reliability, performance optimization, and the operational realities of running services at scale. Hands-on LLM/ML systems experience: You've worked with LLMs in production—whether fine-tuning models, building inference pipelines, optimizing for latency/cost, or evaluating model performance. You're comfortable with frameworks like TensorFlow, PyTorch, or Triton, and you understand the engineering challenges of productionizing ML. Technical depth and breadth: You're T-shaped—deep expertise in at least one area (e.g., ML infrastructure, backend systems, performance optimization) with broad understanding across software engineering. You're the go-to expert in your domain and can quickly come up with effective solutions. End-to-end ownership: You take complex projects from idea through design, implementation, and production with minimal oversight. You launch features smoothly, anticipate risks, and feel responsible for outcomes beyond your immediate scope. Tech stack: Our services are primarily Python-based, as well as Ruby and Typescript, everything running on AWS with Kubernetes. You're comfortable building production services in Python and understand cloud infrastructure. Strong judgment and initiative: You make sound technical decisions in ambiguous situations, knowing when to be creative vs. pragmatic. You have a track record of taking initiative across multiple areas and coordinating solutions that cut across teams. Mentorship and collaboration: You enable others to do their best work. You're comfortable guiding junior engineers, providing constructive code reviews, and adapting your communication style to your audience. You build productive relationships and promote team spirit. Pragmatic problem-solving: You identify technical debt and tackle it strategically. You seek empirical evidence to validate ideas. You balance short-term needs with long-term architecture. You know when to make tradeoffs and can clearly articulate scalability and reliability constraints. At Entrust, we don’t just offer jobs – we offer career journeys. Here is what you c an expect when you join our team: Career Growth: Whether you’re a budding developer or a seasoned expert, we’re invested in your professional journey. With learning-forward initiatives and exciting challenges, your growth is our priority. Flexibility: Life is all about balance. Whether you’re remote, hybrid, or on-site, we offer flexible options that fit your lifestyle. Collaboration: Here, your voice matters. Our teams thrive on sharing ideas, brainstorming solutions, and working together to build a better tomorrow. We believe in securing identities—but it doesn’t stop there. At Entrust, we’re passionate about valuing all identities. Our culture is built on diversity, inclusion, and respect. From unconscious bias training for our leaders to global affinity groups that connect colleagues across the globe, we’re creating a community where everyone is encouraged to be themselves. Ready to Make an Impact? If you’re excited by the prospect of innovating, growing your career, and collaborating in a dynamic environment, Entrust is the place for you. Join us in making a difference. Let’s build a more secure world—together. Apply today! For more information, visit www.entrust.com .  Follow us on, LinkedIn , Facebook , Instagram , and YouTube For US roles, or where applicable: Entrust is an EEO/AA/Disabled/Veterans Employer For Canadian roles, or where applicable: Entrust values diversity and inclusion and we are committed to building a diverse workforce with wide perspectives and innovative ideas. We welcome applications from qualified individuals of all backgrounds, and we strive to provide an accessible experience for candidates of all abilities. If you require an accommodation, contact [email protected] . Recruiter: Jack Steib [email protected]