About the Project
We are building a next-generation internal AI platform for working with corporate knowledge, automating processes, and orchestrating specialized AI agents.
The system integrates data from various internal sources, forms a unified corporate knowledge space, assists in decision-making, and automates parts of operational activities using AI.
We are looking for a strong engineer who can take on the full lifecycle of AI system development: from working with data and RAG infrastructure to building agent architecture and deploying solutions to production.
This is not a research role or a prompt engineer position. We need a practical engineer capable of independently designing, developing, and scaling production AI systems.
What you will be doing
- Designing and developing the company's internal AI platform.
- Integrating data from various corporate systems and sources.
- Building data processing, cleaning, normalization, and indexing pipelines.
- Developing and optimizing RAG systems.
- Working with vector databases and retrieval architecture.
- Designing AI agent memory architecture.
- Developing and maintaining multi-agent systems.
- Implementing agent orchestration based on LangGraph.
- Creating tools, MCP integrations, and internal services for agents.
- Managing context, memory, and interaction between agents.
- Optimizing response quality, request costs, and system performance.
- Developing evaluation pipelines and quality control mechanisms.
- Participating in key architectural decision-making.
Mandatory Requirements
- 5+ years of commercial development experience.
- Experience in creating production AI products.
- Excellent command of Python.
- Practical experience in building RAG systems.
- Experience with embeddings and retrieval pipelines.
- Experience with LangGraph.
- Practical experience in developing AI agents and multi-agent systems.
- Commercial experience with LLMs for at least 2-3 years.
- Understanding of AI system memory architecture and context management.
- Experience with PostgreSQL.
- Experience with pgvector, Qdrant, Weaviate, or similar vector databases.
- Experience preparing, processing, and indexing large volumes of data.
- Experience with Claude, OpenAI, Gemini, or similar LLM APIs.
- Understanding of agent orchestration and inter-agent interaction.
- Experience integrating external services, APIs, and tools.
- Proficient with Git and code review.
Will be a plus
- Experience with MCP (Model Context Protocol).
- Experience in building evaluation frameworks.
- Experience with LangSmith, Langfuse, Galileo, or similar observability tools.
- Machine Learning Engineering experience.
- Experience in fine-tuning open-source models.
- Experience with the Anthropic ecosystem.
- Experience in designing complex AI workflows and long-term memory systems.
Who we are looking for
We need a hands-on engineer who can independently bring solutions to production.
This is not a role for an architect who only makes decisions, nor a researcher who works exclusively with experiments.
We are looking for someone who is capable of:
- Independently learning new tools.
- Writing code daily.
- Making technical decisions and taking responsibility for the results.
- Building systems end-to-end.
- Working with high autonomy and responsibility.
You will be the first AI engineer for the product and will have significant influence on the architecture, technical decisions, and future development of the platform.
Conditions
- Fully remote work.
- Long-term cooperation.
- Small team and fast decision-making cycles.
- Direct interaction with the CEO and CTO.
- High degree of influence on product development.
- Payment in USDT or another currency convenient for the candidate.
- Salary range: 4,000–9,000 USD per month.
