Talent Pool_Applied AI Engineer_Europe

Alcor; Warszawa; On-site; PLN 120,000 - 180,000; Full time

Job summary

Alcor is seeking an engineer to ship AI features to production, bridging backend systems and AI integration. You will build APIs, retrieval pipelines, and agent workflows to turn language models into reliable product features.

You will work with OpenAI, Claude, and Gemini APIs, design REST/gRPC services, and implement RAG pipelines with embeddings and vector stores. Docker, Kubernetes, and AWS experience are valued.

Qualifications

• Strong Python skills used as backbone for backend and AI integration work.
• Track record of shipping AI features to production beyond model experimentation.
• Hands-on experience with LLM APIs, RAG pipelines, embeddings, and vector databases.

Responsibilities

• Build production AI systems and integrate LLM APIs into product workflows.
• Design and build backend APIs (REST and gRPC) and scalable microservices for AI features.
• Develop RAG pipelines using vector databases and embeddings and ensure reliable retrieval.
• Implement agent-based architectures and workflow orchestration.
• Set up monitoring, evaluation, and optimization for AI systems in production.
• Handle prompt engineering and iterate on performance based on real usage.
• Collaborate with product and data teams to ship reliable, measurable AI features.

Skills

Python

Async processing

Distributed systems

SQL & data handling

Tools

OpenAI API

Claude API

Gemini API

Docker

Kubernetes

AWS

REST

gRPC

RAG pipelines

Vector databases

Embeddings

LangChain

Kafka

RabbitMQ

Job description

An engineer who ships AI features to production. This role bridges backend systems and AI integration, building the APIs, retrieval pipelines, and agent workflows that turn language models into reliable product features.

Responsibilities:

• Build production AI systems and integrate LLM APIs (such as OpenAI, Claude, and Gemini) into product workflows.
• Design and build backend APIs (REST and gRPC) and scalable microservices that serve AI features.
• Develop RAG pipelines using vector databases and embeddings.
• Implement agent-based architectures and workflow orchestration.
• Set up monitoring, evaluation, and optimization for AI systems running in production.
• Handle prompt engineering and iterate on performance based on real usage.
• Work closely with product and data teams to ship reliable, measurable AI features.

Qualifications:

• Strong Python skills, used as the backbone for backend and AI integration work.
• A track record of shipping AI features to production, beyond model experimentation.
• Hands-on experience with LLM APIs, RAG pipelines, embeddings, and vector databases.
• Solid backend foundations: API design, microservices, and distributed systems.
• Experience with cloud infrastructure, with AWS preferred.
• Comfort with Docker. Kubernetes is a plus.
• Working knowledge of SQL and data handling.
• Familiarity with async processing and message queues (Kafka or RabbitMQ) is a plus.
• Exposure to orchestration frameworks such as LangChain is a plus.