What you need to know about the job

AI Technical Lead

Are you an AI technical lead ?

Education and Expertise:
  • Experience: 5+ years Python & C#, including building REST/GraphQL APIs and LangChain or SK pipelines
Technical Qualifications:
  • Hands-on with Ollama: installing, running models ≥ 7B, exposing REST endpoints, and integrating via SDKs
  • RAG & Vector Stores: designing embeddings flow, chunking, and caching for local‐first retrieval
  • GPU/Hardware optimization: quantization, batching, NUMA awareness; able to articulate minimum specs for 7–13B models

Responsibilities

  • Package, pull, and tune Llama-class models with Ollama’s CLI & REST API; manage model files and versioning
  • Profile CPU/GPU utilization, quantization levels (4-bit, Q K), VRAM needs, and Node feature gates
  • Build RAG pipelines that ground Ollama models with Azure AI Search (vector + hybrid) and local embeddings
  • Compose cross-boundary workflows: SK Ollama connector for local inference, SK Azure OpenAI connector for cloud scale; implement planners and memory stores
  • Benchmark token latency vs. cloud; decide burst thresholds; recommend hardware upgrades
  • Train engineers on LangChain-Ollama patterns, SK plugin authoring, and hybrid deployment trade-offs

Apply now

Fields with (*) are required.