AI Engineer

📌 ACTUAL LOCATION: ASTANA, KAZAKHSTAN

Armeta is an applied-AI company building engineering-intelligence products for construction and oil & gas.

We're opening an AI Engineer position on a new product squad working in structural analysis and design based on the finite-element method. The team is small — a business analyst and an AI Engineer, as its technical core, you own the outcome: from hypothesis to a working MVP in the hands of first users.

What you'll do

• Own the product's AI/ML layer end to end — from prototype to production MVP.
• Build agentic LLM pipelines: orchestration, tool/function calling, structured output, long-context handling, model routing, and cost/latency control.
• Implement natural-language-to-calculation-model translation: parsing an engineer's requirements into a structured model representation (nodes, elements, sections, constraints, loads), validation, and reverse generation.
• Design RAG over the normative base (SP/SNiP/Eurocodes).
• Ship AI features for the structural engineer: FE-mesh generation and load-definition assistance, result interpretation, and model-error diagnosis and explanation.
• Integrate the AI layer with the compute engine / solver and the product frontend via REST/WebSocket APIs.
• Build eval pipelines and quality metrics: golden datasets, regression runs, and offline/online evaluation, so keep/kill decisions on each hypothesis are objective.
• Run a fast "hypothesis → prototype → test → production" loop.
• Work closely with a business analyst who brings the structural-engineering expertise.

Requirements

• Python - 2+ years of commercial experience, with deep command of async (asyncio), typing, Pydantic, and clean architecture.
• FastAPI and production-API design: REST, WebSocket, background processing, task queues (Celery / RQ / arq).
• Strong proficiency with Claude Code and its full toolset: subagents, MCP servers, hooks, custom slash commands, CLAUDE.md and context/memory management, plan mode, skills, headless mode.
• Hands-on LLM experience in production: agent frameworks (LangGraph and similar), function/tool calling, structured outputs, RAG, embeddings and vector DBs (pgvector / Qdrant / Weaviate), fine-tuning, and building and analyzing metrics and evals.
• PostgreSQL and data handling.
• Experience taking a product to MVP in a small team: backend, APIs, integrations.
• Product thinking and the ability to work autonomously.

Nice to have

• Background in structural / civil engineering; understanding of the finite-element method, strength of materials, and calculation models.
• Computational geometry, numerical methods, sparse matrices and solvers (numpy / scipy).
• CAD/BIM: IFC, DWG/DXF, geometry handling and parsing of engineering formats.
• Experience launching products from scratch.