Senior AI/LLM Engineer | Python & FastAPI (Remote)

Kake; Warszawa; À distance; PLN 586 000 - 742 000; Plein temps

Avantages offerts par ce poste

Fully Remote

Competitive USD Pay

Better Me Fund

Social good community

Résumé du poste

Kake, a remote-first, people-first global community of senior engineers, is seeking a Senior AI/LLM Engineer with strong Python to design, build, and productionize LLM-powered applications at scale. You’ll operate at the intersection of software engineering and applied AI, taking ownership from prototyping through production deployment.

You’ll build backend services (FastAPI), develop RAG pipelines, integrate with OpenAI/Anthropic APIs, and work with containers, PostgreSQL, Redis, and vector

Qualifications

• Strong Python proficiency and experience with FastAPI or similar.
• Experience with LLM APIs (OpenAI, Anthropic) and LangChain.
• Experience with RAG architectures, embeddings, vector databases.
• Hands-on Docker and containerized development.
• Experience with PostgreSQL/Redis.
• Strong English communication and independent work style.
• Ability to work remotely in a fast-paced environment.

Responsabilités

• Design, build, and deploy LLM-powered features and applications using Python.
• Develop and maintain backend services and APIs exposing AI/LLM capabilities.
• Build and optimize RAG pipelines, embeddings, and vector search.
• Design and iterate prompts, agents, and orchestration flows.
• Integrate with LLM providers and manage costs, latency, and quality.
• Evaluate model outputs with tooling and metrics for QA.
• Work with containerized environments and data stores to support production systems.
• Collaborate with cross-functional stakeholders to translate needs into AI solutions.

Connaissances

Python

FastAPI

LLM APIs

LangChain

RAG

Embeddings

Vector databases

Docker

PostgreSQL

Redis

Testing AI models

English communication

Outils

Docker

Description du poste

Kake, a remote-first, people-first global community of senior engineers, is seeking a Senior AI/LLM Engineer with strong Python to design, build, and productionize LLM-powered applications at scale. You’ll operate at the intersection of software engineering and applied AI, taking ownership from prototyping through production deployment.

You’ll build backend services (FastAPI), develop RAG pipelines, integrate with OpenAI/Anthropic APIs, and work with containers, PostgreSQL, Redis, and vector