Mid-Level Software Engineer
protocols (e.g., MCP, A2A) - Familiarity with running language models locally (e.g., using HuggingFace transformers, ollama...
protocols (e.g., MCP, A2A) - Familiarity with running language models locally (e.g., using HuggingFace transformers, ollama...
to support frontend functions Learn about and compare AI and Machine Learning algorithms Utilize agentic framework, MCP, Ollama...
models such as Qwen and Ollama-based deployments, using quality, latency, cost, security, privacy, and platform-fit criteria... hosted model platforms, including tools such as Ollama and models such as Qwen. Work Experience Required: Demonstrated...
protocols (e.g., MCP, A2A) - Familiarity with running language models locally (e.g., using HuggingFace transformers, ollama...
knowledge of the open-model ecosystem, including tools such as Hugging Face, PyTorch, Ollama, SGLang, or vLLM. Ability to read...
with external systems and engineering data.Familiarity with local or on-premises AI infrastructure and technologies such as Ollama... such as Ollama, Open WebUI, vLLM, Hugging Face, or similar tools.Experience with Protocol Buffers (Protobuf) and RPC frameworks...
domains and optimize them for edge device performance, including ONNX, GGML, or Ollama. Develop evaluation frameworks...
, Google ADK, LangChain, etc.) LLM APIs and/or open-source models (e.g., via OpenAI, Google, Hugging Face, Ollama) Vector...
routing (Vertex AI for stakes, self-hosted Ollama for volume) — ensuring every agent capability is a governed capability...
. Inference Tools: Proven hands-on experience with tools like vLLM, TensorRT, Llama.cpp, and Ollama for inference development...