Requirements

Expected technologies

Python

OpenAI

FastAPI

NLP

Vector databases

Classical ML

Docker

Git

Operating system

Windows

macOS

Our requirements

• 5+ years of commercial experience in AI/ML, including production projects involving LLMs or agents.
• Strong proficiency in Python and at least one additional language (e.g., TypeScript/Node.js, Java).
• Experience with the API/SDK of at least one major LLM provider (e.g., OpenAI, Anthropic, Google).
• Proficiency in prompt engineering and prompt testing (A/B testing, evaluation harnesses, hallucination testing).
• Knowledge of natural language processing (NLP) methods — both classical and LLM-based — and experience applying NLP to real-world problems.
• Familiarity with vector databases and semantic search engines.
• Skills in working with REST APIs, relational and non-relational databases.
• Experience with configuring services on cloud platforms (e.g., AWS, Azure, GCP).
• Familiarity with AI model deployment tools (Docker, Kubernetes, FastAPI).
• Understanding of AI security, privacy, and regulatory topics.
• Very good command of English.

Optional

• Experience with LangChain, LlamaIndex.
• Experience with tools for LLM evaluation and monitoring.
• Familiarity with fine-tuning and distillation techniques and deploying large language models.
• Experience with multimodal models (text – image – audio).
• Experience with graph databases (e.g., Neo4j) and long-term memory concepts for agents.
• Use of tools for monitoring and managing the AI model lifecycle.
• Ability to automate CI/CD processes and knowledge of DevOps practices.
• Experience in AI-related security and privacy, data governance, sensitive data masking (PII masking), and regulatory compliance.

Your responsibilities

• Designing and developing advanced AI solutions that address real business needs.
• Working across the full project lifecycle — from requirement definition and proof of concept, through production deployment, to inference cost monitoring and optimization.
• Collaborating with frontend, backend, and product teams in designing AI solutions.
• Designing and implementing Retrieval-Augmented Generation (RAG) systems: building pipelines, retrievers, scoring mechanisms, and working with vector databases.
• Creating and integrating AI agents using frameworks such as LangChain, LlamaIndex, and workflow orchestration tools.
• Integrating large language models (LLMs) with a variety of systems — APIs, databases, documents, knowledge graphs, and multimodal models.
• Supporting architecture, data security (data governance, PII masking, compliance), and AI best practices.
• Implementing, deploying, and serving models.
• Conducting code reviews, architecture reviews, and mentoring junior engineers.
• Continuously developing both your own skills and those of the team through knowledge sharing, mentoring, and keeping up with the latest AI trends.