AirflowApolloAWSDockerDynamoDBETLGraphQLKafkaPandasPostgresPythonSDLCSQLTerraformAIMLLarge Language ModelsOpenAIClaudeAnthropicMLflowELTData EngineeringECSLambdaS3RDSSQSVertex AIPostgreSQLDatadogProblem Solving
About this role
Role Overview
Integrate large language models into production AI agent workflows
building structured-output pipelines with grounding, reference resolution, and evidence traceability.
Design and evolve APIs that serve risk Intelligence data to customers and external integrations.
Build and maintain data ingestion pipelines
owning the full lifecycle from extraction through loading and error handling.
Own reliability of async task processing systems — health monitoring, autoscaling, alerting, and incident response.
Build and maintain shared libraries and internal developer tooling that accelerate the entire engineering team.
Manage full service lifecycle — from standing up new services to decommissioning legacy ones.
Requirements
4+ years of experience in Data Engineering or Backend Engineering with a strong data focus.
4+ years of production Python experience
you write clean, testable, well-structured code.
Experience designing and building APIs (preferably GraphQL with Apollo Federation).
Experience in developing, maintaining, and ensuring the reliability, scalability, fault tolerance, and observability of data services in a production environment.
Have fundamental knowledge of data engineering techniques: ETL/ELT, batch and streaming, DWH, Data Lakes, distributed processing.
Comfortable with async Python patterns (asyncio, Celery, task queues).
Strong knowledge of SDLC and solid software engineering practices.
Familiar with infrastructure-as-code approach.
Demonstrated curiosity through asking questions, digging into new technologies, and always trying to grow.
Strong problem solving and the ability to communicate ideas effectively.
Self-starter, independent, likes to take initiative.
Familiarity with at least some of the technologies in our current stack: Core: Python, Pandas, Polars, Celery, SQL (PostgreSQL), SQLAlchemy, Airflow, Docker, Kafka; AI/ML: OpenAI, Anthropic, Google Vertex AI, Pydantic (v2), Pydantic AI, MLflow; APIs: GraphQL (Strawberry); AWS: S3, Batch, RDS, DynamoDB, ECS, SQS, DMS, Lambda; Infra & Ops: Terraform, Datadog.
Experience with or strong interest in AI-native development workflows (we use Claude Code as a core part of how we build software
from building internal tooling skills to debugging production issues.
Tech Stack
Airflow
Apollo
AWS
Docker
DynamoDB
ETL
GraphQL
Kafka
Pandas
Postgres
Python
SDLC
SQL
Terraform
Benefits
Option to work as a B2B contractor or full-time employee
Competitive salary at a well-funded, fast-growing startup
PTO days so you can take the time you need to refresh!
Full-time employees: 28 PTO days allotted + paid public holidays
B2B contractors: 15 PTO days allotted + paid public holidays
100% remote work (or hybrid if you prefer! We have coworking space in center of Warsaw.)