(Triton, TensorRT, VLLM, TGI, etc.). Familiarity with MLOps practices for CI/CD, continuous training, observability... with unauthorized third parties. Guidehouse does not accept unsolicited resumes through or from search firms or staffing agencies...
-critical use cases like Ads, Groceries, Logistics, Fraud, and Search. About the Role We're looking for a Staff Software..., networking, dev platform) and with applied ML teams across Ads, Fraud, Logistics, Search, and more who depend on our platform...
to offer may be impacted if you do not accept all cookies. Modify Cookie Preferences Accept All Cookies Search... in DC/cloud (orchestration, provisioning) with AI workloads and GPU scheduling (K8s, NCCL, Triton). Prior work...
to offer may be impacted if you do not accept all cookies. Modify Cookie Preferences Accept All Cookies Search... with vector stores (e.g., Pinecone, FAISS, Azure Cognitive Search) and prompt strategies;optimize for latency/cost/accuracy...
, SYCL) Experience with model deployment software libraries and stacks (e.g. NVIDIA TensorRT, Triton Inference Server... whether your experience aligns with the requirements of this position, we encourage you to search on , and apply for roles...
to offer may be impacted if you do not accept all cookies. Modify Cookie Preferences Accept All Cookies Search..., FAISS, Azure Cognitive Search) and prompt strategies;optimize for latency/cost/accuracy. Architect agentic AI components...
to offer may be impacted if you do not accept all cookies. Modify Cookie Preferences Accept All Cookies Search... in DC/cloud (orchestration, provisioning) with AI workloads and GPU scheduling (K8s, NCCL, Triton). Prior work...
We are hiring immediately for a full time FOOD UNIT LEAD position. Location: Triton Central Schools - 4920 West 600... Referral Bonus Available We Make Applying Easy! Want to apply to this job via text messaging? Text JOB to 75000 and search...
, SLMs, computer vision) using Ray Serve, vLLM, Ollama, or TensorFlow Implement search and indexing solutions... in production (Ray Serve, vLLM, Ollama, TorchServe, Triton, etc.) Understanding of RAG (Retrieval-Augmented Generation...
) and design efficient similarity search, retrieval workflows, and indexing strategies. Data Ingestion & Processing Pipelines...-serving infrastructure, such as Amazon SageMaker, NVIDIA Triton, Ray Serve, or similar platforms. Hands-on experience...