Forward Deployed AI Engineer (Python, LLMs, RAG) Geo Turkey, Croatia, Czech Rep

Gramian Consultancy is a boutique consultancy specializing in IT professional services and engineering talent solutions. With a strong background in software engineering and leadership, we help companies build high-performing teams by matching them with professionals who truly fit their needs.

Role Overview

We are looking for an experienced Forward Deployed AI Engineer to design and deliver production-grade AI applications directly with enterprise product and engineering teams.

This is a highly hands-on, client-facing role focused on turning complex business requirements into scalable solutions using Python, Large Language Models, RAG, agentic workflows, LangChain / LangGraph, and modern web technologies . You will own the full delivery lifecycle, from discovery and rapid prototyping through production deployment, adoption, and continuous optimization.

CONTRACT: Contractor, long-term engagement

COMMITMENT: Full-time

LOCATIONS: Remote — Turkey, Croatia, Czech Republic, Estonia, Georgia, Poland, or Romania

START: ASAP

DURATION: 6+ months, with possible extension based on performance

NOTES: Fluent English and strong stakeholder communication skills are required.

Key Responsibilities

• Work directly with business, product, and engineering stakeholders to understand complex requirements and translate them into production-ready AI solutions .

• Design and build applications using LLMs, RAG, AI agents, tool/function calling, and structured outputs .

• Develop agentic workflows using frameworks such as LangChain, LangGraph, LlamaIndex, or similar technologies .

• Design retrieval architectures using vector search, embeddings, document pipelines, and contextual retrieval techniques.

• Build robust backend services and application logic in Python .

• Develop user-facing AI applications using React, Next.js, or similar frontend technologies .

• Integrate AI applications with enterprise APIs, internal platforms, data systems, and authentication / IAM environments.

• Deploy applications using cloud platforms, Docker, and CI/CD pipelines .

• Monitor and improve AI application quality, reliability, latency, security, and business performance.

• Contribute reusable engineering patterns, components, and implementation best practices across projects.

Requirements

• 6+ years of professional software engineering experience , with strong production-level Python expertise.

• Hands-on experience building LLM-powered applications in production.

• Strong experience with LangChain, LangGraph, LlamaIndex, or comparable AI orchestration frameworks .

• Strong understanding of Retrieval-Augmented Generation (RAG), vector retrieval, embeddings, and LLM integration patterns .

• Experience designing AI agents, agentic workflows, tool/function calling, structured outputs, and automation systems .

• Experience with React, Next.js, or similar modern web technologies .

• Experience deploying production applications using cloud platforms, Docker, and CI/CD .

• Strong understanding of enterprise integrations, secure API design, IAM, and AI / LLM-specific security considerations.

• Strong ability to translate business needs into technical architecture and communicate effectively with both technical and non-technical stakeholders.