AI Developer
Core
Building and operating LLM-powered systems, including serving open-source models, developing RAG pipelines, and creating MCP integrations.
Role type
hands-on AI developer (LLM engineering)
Builds
LLM-powered features, RAG pipelines, and backend services for ML inference
Domain
Artificial Intelligence / Large Language Models / Cloud Infrastructure
Deliverable
production ML models
Required skills
Python, LLM integration, RAG pipelines, MCP integrations, Docker, CI/CD, Azure, AWS, Linux/Windows admin, scripting (Bash/PowerShell), observability
Preferred skills
GPU/CUDA tuning, model quantization, Terraform, Kubernetes, Kafka, Go, Rust, C++, DevSecOps
Responsibilities
Serve and operate open-source LLMs using Ollama and llama.cpp; Build and maintain RAG pipelines with embeddings and vector databases; Develop MCP integrations connecting LLMs to tools and data; Build backend services in Python for ML inference; Parse and process structured and semi-structured data; Build and maintain CI/CD pipelines for AI services; Deploy AI workloads to cloud providers and containerize services; Automate operational tasks and troubleshoot across the stack