AI Software Engineer

🚀 We are looking for a Middle AI Engineer to build scalable AI-powered applications, developer tools, and workflow automation solutions that improve engineering productivity and deliver measurable business value.

This role is ideal for a strong Python engineer with hands-on experience building and deploying LLM-based applications. You will work on solutions involving RAG, AI agents, model integrations, backend services, and AI evaluation.

🎯 Responsibilities

- Design, build, and deploy LLM-powered applications from prototype to production.

- Develop AI agents, tool-using workflows, and multi-step automation solutions.

- Build and improve RAG pipelines using internal and third-party data sources.

- Integrate commercial and open-weight models such as OpenAI, Anthropic Claude, Google Gemini, and Llama-based models.

- Develop AI-powered capabilities such as code assistance, document generation, summarisation, knowledge search, and workflow automation.

- Build backend services, APIs, integrations, and data flows using Python.

- Implement embeddings, vector search, reranking, structured outputs, and tool calling.

- Evaluate AI outputs and improve relevance, accuracy, reliability, latency, and cost efficiency.

- Add logging, monitoring, error handling, fallback mechanisms, and output validation to AI systems.

- Deploy and maintain AI services in cloud environments.

- Collaborate with product, engineering, and business teams to deliver production-ready AI solutions.

🧩 Requirements

- 3+ years of commercial Python development experience.

- Hands-on experience building and deploying LLM-powered applications.

- Practical experience with at least one of the following:

  - RAG systems;

  - AI agents;

  - multi-step LLM workflows.

- Experience developing backend systems, REST APIs, integrations, and data flows.

- Experience with FastAPI, Django, Flask, or another Python backend framework.

- Hands-on experience with LangChain, LangGraph, LlamaIndex, or a similar AI orchestration framework.

- Experience working with OpenAI, Anthropic, Gemini, Llama-based models, or similar technologies.

- Practical understanding of prompt design, structured outputs, tool calling, and output validation.

- Experience with embeddings, vector search, and at least one vector database.

- Understanding of RAG concepts such as chunking, retrieval, reranking, and response generation.

- Experience evaluating and improving LLM output quality.

- Experience with Docker, Git, automated testing, and CI/CD workflows.

- Experience deploying applications to AWS, Azure, GCP, or another cloud platform.

- Understanding of common production AI challenges, including hallucinations, latency, rate limits, reliability, and cost control.

- English level: Upper-Intermediate or higher.
 

🧩 Nice to Have

- Experience with multi-agent systems.

- Experience building custom tools for AI agents.

- Familiarity with MCP servers, clients, or MCP-based integrations.

- Experience with LLM evaluation and observability tools such as LangSmith, Langfuse, Arize Phoenix, or similar.

- Experience with advanced retrieval techniques, hybrid search, or retrieval evaluation.

- Experience working with open-weight models and model-serving solutions.

- Familiarity with AI safety, guardrails, prompt injection protection, and responsible AI practices.

- Experience with Kubernetes or scalable AI service deployment.

- Experience building AI-powered developer tools.

🧩You'll have an opportunity to:

Build production-ready AI applications used by real users.

Work with modern LLM technologies, AI agents, and RAG systems.

Collaborate with experienced international engineering teams.

Gain hands-on experience with rapidly evolving AI frameworks and cloud platforms.

Solve challenging engineering problems and contribute to scalable AI solutions.

Continuously grow your expertise in Generative AI and modern software engineering