Platform Engineer

Role Software Engineer (AI Agent Platform) Location San Jose, CA (Onsite) Client - Confidential Rate - $90 Interview Mode - Face to Face Duration - 12+ Months (Possibility of extension)

Build and enhance an internal AI agent platform that empowers Cisco employees to interact with enterprise knowledge through conversational interfaces (Webex, web).

Design and develop multi-agent workflows powered by Large Language Models (LLMs) to automate knowledge retrieval, content generation, and competitive analysis at scale.

Architect resilient data ingestion pipelines that synchronize and index unstructured content from sources like SharePoint, Confluence, and internal wikis through Microsoft Graph and other enterprise APIs.

Collaborate with product managers, AI/ML engineers, and InfoSec partners to deliver secure, observable, and high-quality solutions in an agile environment.

Contribute to architecture, retrieval-augmented generation (RAG) design, prompt engineering, and CI/CD practices that support rapid, reliable delivery of AI features.

Succeed in this role by shipping maintainable, production grade agentic systems that measurably improve employee productivity and advance Cisco's AI enabled platform strategy.

• Bachelor's degree with 5+ years of related experience, or Master's degree with 2+ years of related experience, or PhD with 0+ years of related experience.
• Strong proficiency in Python 3.10+ with experience building production services using FastAPI , Pytest , and asynchronous programming patterns (asyncio, httpx).
• Hands-on experience with LLM orchestration frameworks such as LangGraph , LangChain , LlamaIndex , or equivalent agentic frameworks.
• Experience designing and querying relational databases, preferably PostgreSQL (including JSONB, full-text search, and pgvector or similar vector extensions).
• Working knowledge of JavaScript / TypeScript and at least one modern frontend framework (Angular, React, or Vue) for building chat or admin UI surfaces.
• Experience with microservices , containerization ( Docker , Kubernetes ), and at least one major cloud platform ( AWS , Azure , or Google Cloud Platform ).
• Experience integrating AI/LLM features into production applications, including prompt engineering, retrieval-augmented generation (RAG), embeddings, and tool/function calling.
• Familiarity with RESTful API design , OAuth2 / OIDC authentication flows, and secure API integration patterns.

• Experience with multi agent orchestration patterns (planner/worker/critic, supervisor graphs, state machines) using LangGraph or similar.
• Experience integrating with enterprise SaaS APIs such as Microsoft Graph , SharePoint, Webex, Salesforce, or ServiceNow.
• Experience with vector databases and embedding stores (pgvector, Pinecone, Weaviate, Milvus, FAISS, OpenSearch k-NN).
• Experience with caching and event driven systems such as Redis , Apache Kafka , or RabbitMQ for real-time data pipelines.
• Experience with chatbot / conversational interface development (Webex Bot SDK, Slack Bolt, Microsoft Bot Framework, or Adaptive Cards).
• Experience with DevOps tools including Jenkins , GitHub Actions , ArgoCD, or Terraform.
• Experience with secrets management ( Hashi Corp Vault , AWS Secrets Manager) and object storage ( MinIO , Amazon S3 , Azure Blob).
• Experience with document processing pipelines , PDF/DOCX/PPTX extraction (PyMuPDF, python-docx, python-pptx), OCR, or computer vision libraries (OpenCV, Pillow) for image filtering.
• Familiarity with LLM observability and evaluation tooling (LangSmith, Langfuse, Arize, Helicone, or RAGAS).
• Strong problem solving, written communication, and stakeholder facing delivery skills , especially in cross functional environments spanning Engineering, IT, and Security.

For applications and inquiries,