Cloud Engineer with expertise in Generative AI in Santa Clara, CA

Position: Cloud Engineer with expertise in Generative AI – Senior GenAi/ Agentic Lead

Location: Santa Clara, CA (Onsite)

Employment Type: Contract

 

Face-to-face interview in the L2 round

 

Agentic ecosystem–Must

We are seeking a highly skilled Senior Cloud Engineer with expertise in Generative AI, Copilot Studio, and multi‑cloud platforms spanning Azure (including Azure AI Foundry), AWS, and Google Cloud. This role will design scalable, secure, and production‑ready AI systems, enabling RAG, agentic workflows, and enterprise copilots.

Core Responsibilities:

1. Architect end‑to‑end Generative AI solutions, including model serving (vLLM, TGI), API integration, and user interaction layers.
2. Design and implement RAG architecture using vector stores, embeddings, hybrid search, and re‑ranking to embed enterprise knowledge into LLMs.
3. Create agentic systems that enable multi‑agent collaboration for complex, stateful workflows and reasoning‑driven automation.
4. Develop and govern Copilots in Copilot Studio, including connectors, actions, plugins, DLP rules, environment strategy, and integration with Microsoft 365 and enterprise systems.
5. Leverage Azure AI Foundry (prompt flow, evaluators, safety, model orchestration) to operationalize LLM applications at scale.
6. Evaluate and optimize AI system performance, balancing quality, latency, throughput, cost efficiency, and safety compliance.
7. Implement Responsible AI, security, and HITL (HumanintheLoop) controls, ensuring compliance in regulated environments) controls, ensuring compliance in regulated environments.
8. Produce clear, maintainable documentation for architecture, patterns, and operational processes.

Required Qualifications

1. 8–10 years of experience in cloud architecture or enterprise software engineering.
2. 3+ years of hands‑on experience designing or delivering Generative AI or LLM applications.
3. Proven experience with Azure AI Foundry, Azure OpenAI, and Copilot Studio (actions, connectors, governance, M365 integration).
4. Experience deploying AI solutions on AWS (Bedrock, SageMaker) and/or GCP (Vertex AI).
5. Hands‑on experience with RAG, vector databases (Azure AI Search, Pinecone, OpenSearch, Vertex Matching Engine), embeddings, and hybrid search.
6. Deep understanding of cloud security (IAM/RBAC, Key Vault/KMS, VPC/PrivateLink, token safety).
7. Experience with Kubernetes (AKS/EKS/GKE), containerization, API frameworks (FastAPI, Node.js, .NET), Python, TypeScript, or C#/.NET.
8. Working knowledge of transformer architectures and model adaptation techniques (fine‑tuning, LoRA, prompt engineering).
9. Familiarity with AI Ops / MLOps tools such as Prompt Flow, MLflow, SageMaker Pipelines, or Vertex Pipelines.

Preferred Qualifications

1. Experience implementing agent‑based systems using frameworks like LangChain, LlamaIndex, Semantic Kernel, or AutoGen.
2. Background working with enterprise data ecosystems (Databricks, Snowflake, BigQuery, Redshift).
3. Knowledge of Responsible AI frameworks, guardrails, safety filters, PII redaction, and evaluation methodologies.
4. Experience in regulated industries (healthcare, finance, government), with an understanding of compliance controls.
5. Experience with observability (OpenTelemetry, Prometheus/Grafana, App Insights) for AI workloads.

Education:

• Bachelor’s/Master's in Computer Science, Engineering, Information Systems, Data Science, or related field (required).

 

Thanks & Regards
Avanish Pandey

Quantum World Technologies Inc.

Avanish@quantumworldit.com || +1 (805) 225-4154