Skip to content
Search jobs inside your AI agent. Claude, ChatGPT, Claude Code, Codex, Gemini, Cursor and Grok
Connect

Uvik Software

NewBe an early applicant

AI Python Engineer

Posted

Summary

Build production-ready AI-powered backend services for international clients: integrating LLMs (OpenAI, Anthropic, Gemini), RAG systems, AI agents, and Python APIs, while improving reliability, latency, and cost of AI workflows. Applied AI engineering role, not ML research.

🚀 We are looking for an experienced AI Python Engineer to build production-ready AI-powered products and intelligent automation solutions.
This role is ideal for a strong Python backend engineer with hands-on experience integrating Large Language Models into real applications. The main focus is applied AI engineering rather than traditional Machine Learning research.

🎯 Responsibilities
Design and develop AI-powered backend services and product features.
Integrate LLM providers such as OpenAI, Anthropic, Google, or open-source models.
Build RAG systems, AI agents, multi-step workflows, and intelligent automation solutions.
Develop APIs and integrations using Python.
Implement prompt management, structured outputs, tool calling, and external service integrations.
Improve the quality, reliability, latency, and cost efficiency of AI workflows.
Implement logging, error handling, fallback mechanisms, and AI output evaluation.
Collaborate with product, engineering, and business teams to deliver AI features from concept to production.

🧩 Requirements
Strong commercial experience with Python backend development.
Experience developing APIs using FastAPI, Django, Flask, or similar frameworks.
Hands-on experience building and deploying LLM-powered applications.
Practical experience with OpenAI, Anthropic, Google Gemini, or similar LLM APIs.
Experience with RAG systems or AI agents and workflows.
Experience with prompt engineering, structured outputs, and tool or function calling.
Experience with Docker, Git, automated testing, logging, and error handling.
Understanding of production LLM challenges, including hallucinations, latency, rate limits, reliability, and cost optimization.
Ability to independently design and deliver solutions from concept to production.
English level: Upper-Intermediate or higher.

🧩 Nice to Have
Experience with LangChain, LangGraph, LlamaIndex, CrewAI, or similar frameworks.
Experience with vector databases such as Qdrant, Pinecone, Weaviate, Chroma, or pgvector.
Experience with LLM evaluation and observability tools such as Langfuse, LangSmith, or Arize Phoenix.
Experience with AWS, Azure, or GCP.
Familiarity with MCP.
Experience with open-source LLMs or model-serving solutions.

⚡️You'll have an opportunity to:
Build production AI products used by international clients.
Work with modern LLMs, AI agents, and RAG architectures.
Design scalable backend services and AI integrations.
Influence technical decisions and architecture.
Continuously explore the latest AI technologies and engineering practices.

🌍 What We Offer:
Paid vacation and sick leave
We provide the equipment you need to work comfortably (if required)
We cover 50% of courses if you want to grow professionally
Regular salary reviews based on your performance
Competitive salary, depending on your experience
Always on-time payments — no delays
A normal, supportive team without unnecessary bureaucracy

Skills

Apply

See also

Software Engineering jobs by country — openings, pay and top skills →