AI Engineer

Sumsub

AI Engineer building Summy AI Copilot, an LLM-powered compliance assistant for Sumsub’s trust infrastructure. Developing agents, retrieval, Text-to-SQL, and production GenAI systems.

Posted 8/5/2026full-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 GenAI/LLM systems, with a strong focus on Python, SQL, and data infrastructure. Proficient in developing secure Text-to-SQL pipelines and optimizing AI agents for complex reasoning and context retention.

Highest-signal resume keywords

GenAI/LLM Systems DevelopmentPython ProgrammingSQL ProficiencyData Infrastructure ExperienceCloud Deployment (GCP/AWS)

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 EngineeringMachine Learning EngineeringText-to-SQL DevelopmentStructured Data ExtractionAgentic OrchestrationMicroservices DevelopmentProduction Metrics AnalysisA/B TestingCompliance Data HandlingCost-Aware Routing

Tools & Technologies

BigQueryKafkaAirflowLangChainLangGraphQdrantFastAPIDockerKubernetesModern LLM APIs

Industry Keywords

ComplianceAnti-FraudKYC/AMLFintechNLPMLOpsData Engineering

Tech Stack

Tools & technologies

AirflowAWSBigQueryCloudDockerGoogle Cloud PlatformKafkaKubernetesMicroservicesPythonSQL

About the role

Key responsibilities & impact

Own the core intelligence behind Summy AI Copilot, taking features from concept to production rollout
Design and build robust multi-turn AI agents capable of complex reasoning, context retention, and autonomous action
Develop hybrid retrieval pipelines using dense retrieval, BM25, reranking, and semantic layers over sensitive compliance data and business glossaries
Build and optimize secure Text-to-SQL pipelines with permission-aware access control, execution previews, and safety guardrails
Set up tracing, monitoring, and evaluation pipelines to track quality, latency, and token cost
Start with solid baselines and iteratively scale complexity using production metrics and A/B tests

Requirements

What you’ll need

5+ years of experience in Software, Data, or ML Engineering
1.5+ years explicitly focused on building and shipping production-grade GenAI/LLM systems
In-depth understanding of how LLMs work under the hood
Experience with structured extraction, tool calling, and cost-aware routing
Strong Python and SQL skills
Experience with data infrastructure including BigQuery, Kafka, and Airflow
Hands-on experience with agentic orchestration using LangChain or LangGraph
Experience with vector databases such as Qdrant or similar
Experience with modern LLM APIs including Claude, Gemini, or OpenAI
Production-ready microservices development with FastAPI
Experience with cloud deployments using GCP or AWS, Docker, and Kubernetes
Nice to have: Text-to-SQL agents or self-service data analytics tools
Nice to have: classical NLP, traditional MLOps, or large-scale data engineering
Nice to have: compliance, anti-fraud, KYC/AML, or fintech experience

Benefits

Comp & perks

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