Описание
Intellias provides technology solutions to business, government, education, and healthcare customers. Its offerings range from hardware and software to integrated IT solutions covering security, cloud, data center, and networking.
Задачи
•Architect complex, multi-agent workflows using the Microsoft AI tech stack
•Design, develop, and deploy agents that handle loops, interruptions, and human-in-the-loop interventions
•Build reliable tool layers that enable LLMs to interact safely with internal APIs, databases, and third-party SaaS platforms
•Design persistence layers for agent memory, conversational history, and context windows
•Build production-grade data retrieval and integration systems
•Optimize vector indexing, document chunking, and re-ranking algorithms for high-precision context retrieval
•Collaborate with Data Engineers to curate Golden Datasets for agent consumption
•Build CI/CD pipelines for AI with LLM-as-a-Judge testing
•Leverage evaluation frameworks to score agent outputs for accuracy, hallucination, and safety before deployment
•Instrument applications with tracing tools to visualize agent reasoning chains, monitor latency, and debug production failures
•Monitor token usage and latency
•Optimize prompt density and caching strategies to maintain high performance at sustainable costs
•Rapidly validate new ideas with state-of-the-art models
•Refactor successful prototypes into maintainable, tested production code
•Evaluate emerging technologies to standardize agent connectivity
Требования
•Bachelor's degree and 5 years of software engineering experience with exposure to AI/ML applications, or 9 years of software engineering experience with exposure to AI/ML applications
•Strong hands-on experience with Python for AI/LLM application development
•Hands-on experience designing and building AI agents or Agentic AI solutions
•Experience integrating and working with LLM model APIs, including OpenAI, Azure OpenAI, Anthropic, or Gemini
•2+ Years of experience building with LLMs
•Deep familiarity with LangChain, LangGraph, or similar state-based frameworks
•Experience with Pinecone, Weaviate, or pgvector
•Knowledge of advanced prompt engineering techniques, including Chain-of-Thought, ReAct, and Few-Shot
•Experience operating AI applications in production, including handling rate limits, context window overflows, and non-deterministic errors
•Ability to explain probabilistic software to non-technical stakeholders and manage expectations about agent accuracy and usefulness
•Excellent communication skills, including documenting technical designs, sharing insights, and enabling team knowledge transfer
Условия
•Remote work is available across Bulgaria, Croatia, Egypt, Germany, India, Poland, Portugal, Spain, and the United Kingdom
•Equal opportunity employer with an emphasis on equity, diversity, and inclusion
•Benefits support employee well-being and professional growth
