Senior AI Engineer — Production-Grade LLM & Agents

Applaudo; Polska; Remote; PLN 550,000 - 786,000; Full time

Job summary

Applaudo is seeking a Senior AI Engineer to design and deploy production-grade LLM and agentic AI systems. You will own MCP server orchestration, integrate hosted LLM APIs, and optimize prompts and latency.

You’ll collaborate with engineers to deliver scalable AI solutions in a contractor model and align with US EDT working hours. The role requires deep Python expertise, production backend practices, and strong English communication for leadership reviews.

Qualifications

• Bachelor's degree in CS, SE, AI, Data Science or related field or equivalent exp.
• Strong Python and backend service practices (APIs, async I/O, typing, testing).
• Solid SQL skills with cloud data warehouses (Snowflake preferred).
• Hands-on prod experience building LLM and agentic AI apps.
• Experience building MCP servers in production and orchestration across steps.

Responsibilities

• Build and maintain MCP servers, tool and resource definitions, and context management.
• Design and implement intent evaluation, classification, and routing workflows across multiple sources.
• Integrate Anthropic and OpenAI models into production environments.
• Manage prompt versioning, fallbacks, and LLM performance optimization.
• Write SQL against model inputs/outputs to support evaluation and monitoring.
• Collaborate with engineers to deliver production-ready AI solutions.
• Work in a partially documented codebase, tracing behavior and making safe changes.

Skills

Python

SQL

LLM Apps

MCP Servers

Prompt Engineering

API Orchestration

English (B2+)

Education

Bachelor's degree or equivalent

Tools

Snowflake

OAuth/OIDC

Job description

Applaudo is seeking a Senior AI Engineer to design and deploy production-grade LLM and agentic AI systems. You will own MCP server orchestration, integrate hosted LLM APIs, and optimize prompts and latency.

You’ll collaborate with engineers to deliver scalable AI solutions in a contractor model and align with US EDT working hours. The role requires deep Python expertise, production backend practices, and strong English communication for leadership reviews.