AI Engineer

Quadcode is hiring an AI Engineer for its AI Platform team to design, build, and maintain production generative AI pipelines and LLM-powered features. The work often includes financial and trading data, with a focus on shipping reliable LLM systems, agentic workflows, MCP tooling, and evaluation pipelines.

Role Responsibilities

• Design, build, and maintain LLM-powered features and pipelines for generative AI products, including pipelines that handle financial and trading content.
• Develop and improve agentic systems and multi-agent workflows, including integrations using MCP (Model Context Protocol) servers and tooling.
• Write production-grade backend Python services on top of LLM provider APIs (OpenAI, Anthropic, xAI) and/or on-premise LLMs.
• Build and iterate on prompt engineering and prompt-evaluation pipelines, including structured output generation and validation.
• Move prototypes and proofs-of-concept into reliable, maintainable production services.
• Monitor and manage trade-offs across LLM cost, latency, and reliability for end-to-end pipelines.
• Work closely with a small, senior AI Platform team on architecture, code review, and technical direction.

Requirements

• Production LLM experience: Experience shipping real, live features using OpenAI and/or Anthropic APIs, or using on-premise/open-weight LLMs, beyond experimentation or side projects.
• Agentic and MCP experience: Hands-on work building multi-agent systems or workflows and integrating with MCP servers.
• Python and engineering fundamentals: 2–4+ years of experience with REST APIs, SQL, Docker, git, and concurrency, with demonstrated ability to take projects from prototype to maintainable production service.
• Practical LLM engineering: Comfort with structured outputs, prompt evaluation, and cost-aware design decisions in production contexts.
• English fluency: Written and verbal.

Technologies

Python, OpenAI, Anthropic, xAI, MCP (Model Context Protocol), REST APIs, SQL, Docker, git, open-weight LLMs, on-premise LLMs, Kubernetes, Kubeflow, Airflow, Hugging Face inference, AWS, GCP.

Location and Work Model

Georgia (hybrid).

Benefits

• Hybrid work model in a brand-new office in Limassol.
• Health insurance and mental health services.
• 13th salary and 21 vacation days per year.
• Sick leave without medical certificate: 3 days per quarter.
• Catered lunches in the office.
• Tuition reimbursement (kindergartens/schools).
• Onsite Gym.
• Corporate events and workshops.
• Bonuses for special events (e.g., child’s birth).
• Birthday and anniversary gifts.
• Company-provided laptop.
• Corporate AI subscriptions (Claude, Gemini, GPT, etc.).
• Access to a rewards marketplace offering products and language courses, redeemable using the company’s internal currency.

Nice to Have

• Prior experience working in fintech.
• Finance and markets knowledge, including tickers, earnings, technical indicators, and forex/CFDs.
• Quant background.
• Experience with model fine-tuning/training, RAG, or LLM optimization techniques.
• Track record in Kaggle competitions focused on LLMs or multi-agent frameworks.
• GPU infrastructure experience, including provisioning GPU compute or serving open-weight models (e.g., Hugging Face inference).
• Experience with Kubernetes, Kubeflow, or Airflow.
• Data analysis and statistics experience.
• Experience with cloud platforms (AWS, GCP, etc.).
• Fluent Russian.