You will work on scalable AI solutions, developer-focused tools, workflow automation, and AI capabilities that improve engineering productivity and deliver real business value for clients.
Responsibilities:
β Design, build, and deploy LLM-based applications and agentic AI systems from prototype to production.
β Develop production-grade AI agents, multi-agent systems, and tool-using workflows.
β Implement RAG pipelines over proprietary and third-party data sources.
β Build and maintain vector databases for AI data storage, retrieval, and search.
β Design and implement AI-powered capabilities such as code assistance, documentation generation, test automation, summarization, knowledge discovery, and code review support.
β Evaluate foundation models such as OpenAI, Anthropic, Gemini, Llama, and other commercial or open-weight models.
β Build LLM evaluation and benchmarking pipelines, including offline tests, online monitoring, human-in-the-loop review, and quality measurement.
β Improve model performance across relevance, faithfulness, latency, throughput, reliability, and cost.
β Design and maintain APIs, backend services, integrations, data flows, and custom tools for AI systems.
β Build custom tools, skills, integrations, and MCP-style server/client patterns for agentic workflows.
β Deploy, monitor, and optimize AI systems on cloud platforms, with a focus on scalability, reliability, observability, and cost efficiency.
Requirements:
β 2+ years of hands-on experience building and deploying LLM-based applications, RAG systems, or AI agents in production.
β Strong Python experience, ideally 3+ years.
β Experience building backend systems, APIs, services, integrations, and data flows.
β Experience with object-oriented programming, backend architecture, design patterns, and production system design.
β Hands-on experience with LangChain, LangGraph, or similar AI orchestration frameworks.
β Strong experience designing agentic AI systems, tool-using agents, or multi-step AI workflows.
β Experience with RAG architecture, including chunking strategies, embeddings, vector databases, reranking, and retrieval evaluation.
β Experience with vector databases such as Pinecone, Weaviate, Qdrant, Chroma, Milvus, or similar.
β Experience with LLM evaluation and benchmarking, including designing evaluation pipelines and measuring model performance.
β Strong prompt design, prompt iteration, and prompt optimization skills.
β Experience working with major model providers or open-weight models such as OpenAI, Anthropic, Gemini, Llama, or similar.
β Cloud experience with AWS, GCP Vertex AI, Azure AI Foundry, or similar platforms.
β Familiarity with AI safety, responsible AI, guardrails, and output validation for production systems.
β Experience with CI/CD pipelines, deployment workflows, and engineering best practices.
We offer:
β remote time job, B2B contract
β 12 sick leaves and 18 paid vacation business days per year
β Comfortable work conditions (including MacBook Pro and Dell monitor on each workplace)
β Smart environment
β Flexible work schedule
β Competitive salary according to the qualifications