AI Developer

Quick Facts

• Role: AI Developer (hands-on AI engineering)
• Focus: Production-grade LLM-powered systems, RAG, and MCP integrations

Description

Build and operate LLM-powered features from prototype to reliable, deployed systems. Serve open-source models using Ollama and llama.cpp, implement RAG pipelines (embeddings, vector retrieval, chunking), and develop MCP integrations that connect LLMs to tools and data. Support DevOps and operations for AI services across CI/CD and cloud deployments.

Responsibilities

• Serve and operate open-source LLMs with Ollama and llama.cpp (local and on-prem)
• Build and maintain RAG pipelines: embeddings, vector databases, chunking strategies, retrieval quality
• Develop MCP integrations connecting LLMs to internal tools and data sources
• Build Python backend services powering ML inference and AI-driven product features
• Parse and process structured/semi-structured inputs (XML/XSD, Office document formats)
• Grow into model optimization: quantization (GGUF), GPU/CUDA tuning, and offline/air-gapped deployments
• Implement and maintain CI/CD pipelines for AI services (Azure DevOps preferred)
• Deploy AI workloads on Azure and AWS; containerize services with Docker
• Automate operational tasks with Python and shell scripting (Bash/PowerShell)
• Troubleshoot end-to-end with a root-cause mindset
• Support event-driven architectures using Apache Kafka (producers/consumers)

Requirements

• 3–5+ years of production engineering experience with Python for building real services
• Hands-on experience serving LLMs via Ollama/llama.cpp
• Experience implementing vector retrieval/RAG pipelines
• Experience developing MCP integrations
• Cloud & infrastructure experience with Azure/AWS deployments and Docker
• CI/CD automation experience (Azure DevOps preferred; GitHub Actions or GitLab CI)
• Familiarity with event-driven architectures using Apache Kafka

Benefits

• Mentorship available as you ramp up in RAG architecture, Kafka, and advanced MCP work