Mid-Level AI Engineer (Python / LLM / RAG / AI Agents)

We are looking for a skilled Mid-Level AI Engineer to design, develop, and integrate intelligent, scalable, production-ready AI solutions.

Experience: 3+ years
Core Stack: Python, FastAPI, LLMs, RAG, SQL, Vector Databases
Additional Skills: AI Agents, API Integration, Docker, AI Evaluation
Nice to Have: Geospatial AI, GIS, Computer Vision, MLOps

About the Role
Our projects involve data-driven applications, interactive dashboards, intelligent automation, complex data processing, and geospatial visualization, including 2D/3D mapping systems.

We value engineers who can turn AI capabilities into reliable product features, not just write prompts or integrate basic LLM APIs.

The ideal candidate has strong Python skills, practical LLM experience, solid software engineering fundamentals, and a problem-solving mindset.

Key Responsibilities

• Design, develop, and maintain AI-powered applications and services.
• Integrate commercial and open-source LLMs into existing systems.
• Build RAG pipelines for document processing, knowledge retrieval, and semantic search.
• Develop AI Agents, tool-calling workflows, and intelligent automation.
• Build scalable AI APIs using Python and FastAPI.
• Process structured and unstructured data from documents, databases, and external services.
• Implement structured outputs, validation, error handling, and fallback mechanisms.
• Optimize AI accuracy, reliability, latency, and operational costs.
• Implement monitoring, logging, caching, and security best practices.
• Collaborate with backend, frontend, and DevOps teams to deliver production-ready AI features.

Required Technical Skills
Python & Backend Engineering

• 3+ years of relevant experience in software development or AI engineering.
• Strong proficiency in Python, FastAPI, and RESTful APIs.
• Understanding of OOP, clean code, modular architecture, and asynchronous programming.
• Experience with PostgreSQL or similar databases.
• Familiarity with Git, testing, debugging, and API integration.

LLMs & Generative AI

• Practical experience integrating LLMs such as OpenAI, Claude, Gemini, or open-source models.
• Strong understanding of prompt engineering, context management, structured outputs, and function/tool calling.
• Knowledge of tokens, context windows, hallucinations, grounding, and model limitations.
• Ability to select and optimize models based on quality, latency, and cost.

RAG & Vector Search

• Hands-on experience designing RAG architectures and retrieval pipelines.
• Knowledge of embeddings, semantic search, and vector databases (pgvector, Qdrant, Pinecone, or Chroma).
• Experience with document ingestion, chunking, indexing, metadata filtering, and retrieval optimization.
• Ability to evaluate and improve retrieval accuracy and response quality.

AI Agents & Automation

• Experience building AI Agents and multi-step LLM workflows.
• Familiarity with LangChain, LangGraph, LlamaIndex, or similar frameworks.
• Understanding of tool execution, agent state, context management, and workflow reliability.
• Awareness of prompt injection, data privacy, and AI security risks.

Deployment & Reliability

• Experience with Docker, Linux, and API deployment.
• Familiarity with CI/CD, logging, monitoring, and environment configuration.
• Understanding of AI evaluation, automated testing, observability, and performance optimization.
• Ability to troubleshoot and maintain AI services in production.

Nice to Have

• Geospatial AI, GIS, GeoJSON, PostGIS, GeoPandas, or spatial data processing.
• Experience with satellite imagery, computer vision, or multimodal AI.
• Familiarity with PyTorch, Hugging Face, fine-tuning, LoRA, or PEFT.
• Experience with Ollama, vLLM, or self-hosted open-source models.
• Knowledge of Redis, message queues, and background processing.
• Familiarity with AWS, Azure, GCP, Kubernetes, or MLOps.
• Experience integrating AI services with .NET backends or React/Next.js applications.

Soft Skills & Expectations

• Strong analytical thinking and problem-solving abilities.
• Ability to independently design and deliver AI features.
• Product-oriented mindset and ownership of technical solutions.
• Clear communication and effective collaboration.
• Commitment to clean, secure, maintainable, and scalable code.
• Curiosity and willingness to learn emerging AI technologies.
• Ability to evaluate technical trade-offs and deliver practical solutions.

How to Apply
If you enjoy building real-world AI applications and solving challenging engineering problems, we'd love to hear from you.

Please share your CV, LinkedIn, GitHub, or examples of relevant AI projects, especially those involving RAG, AI Agents, automation, or production AI integrations.