AI Engineer

Sumsub

. Own the core intelligence behind Summy AI Copilot, an agentic assistant for compliance officers .

Posted 10/22/2026full-timeRemote • United StatesMid-LevelSeniorWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates expertise in building and deploying production-grade Generative AI and Large Language Model systems, with a strong focus on compliance and integration. Proficient in orchestrating AI agents and managing cloud deployments while ensuring system reliability and performance.

Highest-signal resume keywords

Generative AI/LLM Systems DevelopmentLangChain OrchestrationProduction-Ready Microservices in JavaCloud Deployments on GCP or AWSCompliance and Anti-Fraud Knowledge

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

Software EngineeringData EngineeringMachine Learning EngineeringStructured ExtractionTool CallingCost-Aware RoutingAgentic OrchestrationProduction-Grade CodeMicroservices DevelopmentLarge-Scale Data Engineering

Soft Skills

Customer EngagementProblem SolvingCollaboration

Tools & Technologies

LangChainLangGraphJavaDropwizardGCPAWSDockerKubernetesClaude APIGemini API

Industry Keywords

ComplianceAnti-FraudKYCAMLFintechNLPMLOps

Tech Stack

Tools & technologies

AWSCloudDockerGoogle Cloud PlatformJavaKubernetesMicroservices

About the role

Key responsibilities & impact

Own the core intelligence behind Summy AI Copilot, an agentic assistant for compliance officers
Take AI features from concept through production rollout and operation
Design and build robust, multi-turn AI agents capable of complex reasoning, context retention, and autonomous action
Set up tracing, monitoring, and evaluation pipelines to track quality, latency, and token cost
Evolve Sumsub’s public MCP server and Agent Skills for reliable and secure integration with external AI agents
Begin with solid elementary baselines and iteratively scale complexity based on production metrics and A/B tests
Work with customers from early discussions through operating the system in production

Requirements

What you’ll need

5+ years in Software, Data, or ML Engineering
1+ year explicitly focused on building and shipping production-grade GenAI/LLM systems
In-depth knowledge of how LLMs work under the hood
Experience with structured extraction, tool calling, and cost-aware routing
Hands-on experience with agentic orchestration using LangChain or LangGraph
Experience with modern LLM APIs, including Claude, Gemini, and OpenAI
Ability to write production-ready microservices code using Java/Dropwizard
Experience with cloud deployments using GCP or AWS, Docker, and Kubernetes
Ability to own systems from early customer discussions through production operation
Nice to have: background in classical NLP, traditional MLOps, or large-scale data engineering
Nice to have: familiarity with compliance, anti-fraud, KYC/AML, or fintech domains
Nice to have: experience shipping production RAG systems

Benefits

Comp & perks

Remote-first, trust-based culture
No mandatory office days and no attendance trackers
Offices or coworking spaces provided in some locations, with employee choice
Flexible working hours; no fixed 9-to-5 schedule
Birthday holiday
10 personal days each year
Seven sick days without paperwork
Extra time off for Christmas and New Year
Personal development plans and learning opportunities
Role-specific events covered, including design conferences and marketing forums
Financial bonuses for marriage and welcoming a new baby
Fully covered team offsites several times a year
Tools and hardware needed for the role
Equal opportunity and inclusive workplace