Entrust

1 week ago

Senior ML Engineer - Document Extraction

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 23 hours agoStatus: Live

Job Summary

Build high-accuracy document classification and extraction for a Document Fraud team supporting identity verification and secure onboarding. Design and lead end-to-end features from RFC to production deployment, creating training/evaluation pipelines for LLMs/VLMs, optimizing GPU inference for low-latency real-time extraction, and improving labeling workflows. Collaborate across Applied Science, Product, Design, Data Science, and Operations to ensure performance, scalability, reliability, and measurable customer impact.

Location: London, Lisbon

Workplace: Hybrid

Employment Type: Full time

Job Function: Data Science & Machine Learning

Seniority: Mid level

Key Responsibilities

•Deliver highly accurate and performant document classification and extraction solutions across thousands of documents globally in collaboration with cross-functional teams.
•Lead technical design of complex features and systems from RFC through implementation to production deployment, producing designs that age well over time.
•Build and optimize production ML systems by developing repeatable training/evaluation/deployment pipelines for LLM models and engineering solutions for faster, more accurate extraction.
•Champion performance, scalability, and reliability by understanding production operations, proactively addressing technical debt, scoping/staging releases, and measuring success with metrics.
•Drive technical excellence by leading RFCs, reviewing critical code, ensuring code quality via review/testing/documentation, and mentoring engineers through pair programming and guidance.

Key Requirements

•Strong production engineering experience building, deploying, and operating complex systems, including observability, reliability, and performance optimization at scale.
•Hands-on LLM/ML systems experience working with LLMs in production, including fine-tuning, inference pipelines, latency/cost optimization, and model evaluation.
•Comfort with ML frameworks and productionizing ML, including TensorFlow, PyTorch, or Triton.
•Technical depth to own complex projects end to end from design through production deployment with minimal oversight.
•Experience building production services using a stack such as Python, Ruby, and TypeScript on AWS with Kubernetes.

Experience:LLM/MLFraud detectionIdentity verificationDocument processing

Skills:MentorshipCollaborationTechnical judgmentInitiativePragmatic problem-solving

Tech Stack:PythonRubyTypeScriptAWSKubernetesTensorFlowPyTorchTritonLLMsVLMGPU

Company Brief

Entrust

Provides identity, authentication, and secure transaction solutions including public key infrastructure (PKI), digital certificates, encryption, and secure issuance for payments, mobile, and enterprise environments to protect digital identities and critical communications.

Industry: Cybersecurity

Company Size: Enterprise (1,001+ employees)

Growth: Established Company

Funding: Private Equity Backed

Headquarters: Minneapolis, United States

Founded: 1994

Website LinkedIn

Loading job details...

Preparing the role view and application actions.

Entrust

1 week ago

Senior ML Engineer - Document Extraction

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 23 hours agoStatus: Live

Job Summary

Location: London, Lisbon

Workplace: Hybrid

Employment Type: Full time

Job Function: Data Science & Machine Learning

Seniority: Mid level

Key Responsibilities

•Deliver highly accurate and performant document classification and extraction solutions across thousands of documents globally in collaboration with cross-functional teams.
•Lead technical design of complex features and systems from RFC through implementation to production deployment, producing designs that age well over time.
•Build and optimize production ML systems by developing repeatable training/evaluation/deployment pipelines for LLM models and engineering solutions for faster, more accurate extraction.
•Champion performance, scalability, and reliability by understanding production operations, proactively addressing technical debt, scoping/staging releases, and measuring success with metrics.
•Drive technical excellence by leading RFCs, reviewing critical code, ensuring code quality via review/testing/documentation, and mentoring engineers through pair programming and guidance.

Key Requirements

•Strong production engineering experience building, deploying, and operating complex systems, including observability, reliability, and performance optimization at scale.
•Hands-on LLM/ML systems experience working with LLMs in production, including fine-tuning, inference pipelines, latency/cost optimization, and model evaluation.
•Comfort with ML frameworks and productionizing ML, including TensorFlow, PyTorch, or Triton.
•Technical depth to own complex projects end to end from design through production deployment with minimal oversight.
•Experience building production services using a stack such as Python, Ruby, and TypeScript on AWS with Kubernetes.

Experience:LLM/MLFraud detectionIdentity verificationDocument processing

Skills:MentorshipCollaborationTechnical judgmentInitiativePragmatic problem-solving

Tech Stack:PythonRubyTypeScriptAWSKubernetesTensorFlowPyTorchTritonLLMsVLMGPU

Company Brief

Entrust

Industry: Cybersecurity

Company Size: Enterprise (1,001+ employees)

Growth: Established Company

Funding: Private Equity Backed

Headquarters: Minneapolis, United States

Founded: 1994

Website LinkedIn