Founding AI Engineer
What we're looking for
- 3+ years building distributed/backend or ML systems in production
- strong Python (async/FastAPI)
- Kafka/streaming patterns
- protobuf/schemas
- Postgres/Redis
- CI/CD fluency
- Terraform literacy
- track record shipping AI-native, LLM-integrated systems
- familiarity with MCPs
- experience deploying/scaling LLMs/embeddings on AWS
- tuning inference performance
- Warsaw-based (or willing to relocate)
- fluent English
- comfortable with customers
The Founding AI Engineer will be responsible for turning the company's high-level vision into production. This includes formalizing nodes/modules, powering chat and agents with first-class RAG, and running reliable LLM-backed services on AWS. The engineer will work closely with the infrastructure team and adhere to existing CI/CD and Terraform standards.
Key responsibilities include:
- Formalizing and delivering the AI layer, which includes chat, agents, and modules/nodes, while maintaining clear boundaries between deterministic execution and AI assistance.
- Specifying nodes/modules, including contracts (inputs/outputs), lifecycle (versioning, permissions, audit), and providing SDK/CLI for composition/invocation, as well as rollout/revert practices.
- Building LLM-backed services with RAG as a first-class capability for chat suggestions and fast node retrieval in the agent builder, which involves retrieval/indexing, routing, caching, evaluations/guardrails, and telemetry.
- Deploying and running model inference on AWS while adhering to existing CI/CD and Terraform standards, and collaborating with the infrastructure team to meet latency, reliability, and cost targets.
- Designing streaming flows with strong schemas, retries/backpressure, DLQs, and idempotent consumers, and exposing clean APIs for internal tools and MCPs to ensure clear integration patterns.
- Establishing observability and evaluation for AI features, including regression suites, shadowing/A/B testing, SLOs, dashboards, alerts, and runbooks.