Senior ML Engineer, Doc Fraud

Entrust; Greater London; Hybrid; GBP 90,000 - 150,000; Full time

Benefits offered by this job

Career Growth

Flexible work options (remote/hybrid/活

Collaborative culture

Job summary

Entrust is seeking a Senior ML Engineer for Document Extraction to advance high-accuracy document processing across global onboarding workflows. You will work on production ML pipelines, LLM integration, and scalable inference within a hybrid London/Portugal context.

You will collaborate across Engineering, Product, Data Science and Operations, owning features end-to-end and driving measurable improvements in processing speed and extraction accuracy.

Qualifications

• Production systems with focus on observability, reliability, performance and scale.
• Production experience with LLMs, fine-tuning, inference pipelines, latency optimization, or evaluation.
• Deep and broad software engineering knowledge with T-shaped skills.
• End-to-end ownership from idea to production with minimal supervision.
• Experience building and operating Python-based services on AWS with Kubernetes.

Responsibilities

• Collaborate with Applied Science, Product, Design, Data Science and Operations to deliver accurate document classification and extraction for global documents.
• Lead technical design of complex features and RFCs, from concept to production.
• Build and optimize ML systems: training, evaluating, deploying LLMs; optimize GPU inference; design labeling workflows.
• Improve production performance, scalability, and reliability; track dependencies and manage releases.
• Review code, ensure quality through testing and documentation; align with product priorities.
• Mentor engineers through pair programming and technical guidance.

Skills

Production engineering

LLM/ML systems

Technical depth

End-to-end ownership

Mentorship and collaboration

Pragmatic problem-solving

Strong judgment and initiative

Tools

Python

AWS

Kubernetes

TensorFlow

PyTorch

TypeScript

Ruby

Job description

Role and Location

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 are looking for a Senior Software Engineer to join the Document Fraud team, building products that support customers across our offerings, including financial services, driving verification, proof of address, and more. Our team develops fraud-detection capabilities that power identity, processing government identity documents to enable secure document verification, fraud prevention, and smooth customer onboarding experiences.

As a Senior Software Engineer on the Document Extraction team, you will deliver high-accuracy extraction with global document coverage. You will contribute to our Document Verification offerings to help customers create secure onboarding experiences.

To achieve this, you will leverage technology such as VLM/LLMs and traditional ML approaches in production systems at scale, tackling challenges from designing training and evaluation pipelines, optimizing inference for real-time extraction, and integrating as part of our product offering.

The job is done when customers experience the benefits of modern technology.

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, owning RFC through implementation to production deployment. Produce clean, well-reasoned designs that avoid pitfalls and age well over time.
• Build and optimize production ML systems: develop repeatable pipelines for training, evaluating, and deploying LLM models; implement GPU optimizations for inference; design advanced labeling workflows to improve model accuracy; engineer robust solutions delivering measurable customer value through faster processing and more accurate extraction.
• Champion performance, scalability, and reliability by understanding how our systems operate in production; identify and tackle technical debt, scope and stage releases for smooth deployments, and build metrics to measure success empirically.
• Drive technical excellence by leading RFCs, reviewing critical code, ensuring quality through testing and documentation, and balancing priorities. Collaborate with Product to prioritize features and commitments.
• Mentor and enable other engineers through pair programming, technical guidance, and collaborative problem-solving to deliver quality code and grow team skills.
• Coordinate cross-cutting technical work across teams and org boundaries; track dependencies and assign clear owners to issues.
• Contribute to a culture of continuous improvement, psychological safety, and collaboration through squad-based organization, retrospectives, RFCs, DACIs, and cross-functional partnerships.

What We're Looking For

• Strong production engineering experience: Built, deployed, and operated complex systems in production with emphasis on observability, reliability, performance, and scale.
• Hands-on LLM/ML systems experience: Production experience with LLMs, fine-tuning, inference pipelines, latency/cost optimization, or evaluation; familiarity with TensorFlow, PyTorch, or Triton; capable of productionizing ML.
• Technical depth and breadth: T-shaped with deep expertise in at least one area and broad software engineering knowledge.
• End-to-end ownership: Manage projects from idea to design, implementation, and production with minimal oversight.
• Tech stack: Python-based services (plus Ruby and TypeScript), deployed on AWS with Kubernetes; comfortable building production services in Python and understanding cloud infrastructure.
• Strong judgment and initiative: Make sound technical decisions in ambiguity, take initiative across multiple areas, and coordinate cross-team solutions.
• Mentorship and collaboration: Enable others, provide constructive code reviews, and foster team spirit.
• Pragmatic problem-solving: Identify and address technical debt, seek empirical validation, balance short-term needs with long-term architecture, and articulate scalability and reliability constraints.

What We Offer

• Career Growth: We invest in your professional journey with learning-forward initiatives and challenging opportunities.

• Flexibility: Remote, hybrid, or on-site options to suit your lifestyle.

• Collaboration: Your voice matters and teams work together to build a better tomorrow.

Diversity, Inclusion, and Accessibility

Entrust prioritizes diversity, inclusion, and respect. We provide unconscious bias training for leaders and global affinity groups to connect colleagues worldwide. If you require an accommodation, contact [e-mail].

EEO/AA/Disabled/Veterans Employer

Recruiter

Jack Steib

[e-mail]

Entrust is an innovative leader in identity-centric security solutions with a global footprint and partner network, trusted by organizations worldwide.