$50 - $60 USD hourly
Job Title: Python Agentic AI Engineer – Golang
Location: San Jose, CA
Work Model: Hybrid / Onsite (confirm with client)
Experience: 8+ Years
Employment Type: Contract / Long-Term Contract (confirm)
Job Summary
We are looking for an experienced Python Agentic AI Engineer with strong software engineering skills and experience in Golang to design, develop, and deploy intelligent AI agents and scalable backend services. The ideal candidate will have hands-on experience with Generative AI, Large Language Models (LLMs), agentic workflows, API development, and distributed systems.
The engineer will work on building production-grade AI applications that leverage autonomous agents, tool calling, workflow orchestration, and enterprise system integrations.
Key Responsibilities
- Design, develop, and maintain production-grade AI applications using Python and Golang.
- Build agentic AI workflows using frameworks such as LangGraph, LangChain, or similar technologies.
- Integrate LLMs from providers such as OpenAI, Google Gemini, Anthropic, or other enterprise AI platforms.
- Develop multi-agent systems that support planning, reasoning, tool execution, delegation, and context management.
- Implement Model Context Protocol (MCP) integrations and connect AI agents with APIs, databases, and external tools.
- Develop RESTful APIs, microservices, and backend components to support AI-powered applications.
- Implement Retrieval-Augmented Generation (RAG), embeddings, vector search, and knowledge retrieval solutions.
- Build scalable, asynchronous, and event-driven services using distributed systems and messaging technologies.
- Containerize and deploy applications using Docker, Kubernetes, and cloud platforms such as AWS, Azure, or GCP.
- Implement automated testing, AI evaluation, monitoring, tracing, and performance optimization.
- Ensure AI applications meet enterprise requirements for security, reliability, scalability, and data privacy.
- Collaborate with architects, product managers, and engineering teams to deliver production-ready solutions.
Required Qualifications
- 5+ years of professional software development experience.
- Strong hands-on experience developing applications using Python.
- Experience with Golang (Go) for backend development, APIs, or distributed services.
- Practical experience building Agentic AI or Generative AI applications using LLMs.
- Experience with LangGraph, LangChain, LlamaIndex, or comparable AI orchestration frameworks.
- Strong understanding of REST APIs, microservices, asynchronous programming, and distributed systems.
- Experience with prompt engineering, LLM integration, tool calling, and structured outputs.
- Knowledge of RAG, embeddings, vector databases, and semantic search.
- Experience with Git, CI/CD pipelines, automated testing, Docker, and Kubernetes.
- Strong debugging, problem-solving, and communication skills.
Preferred Qualifications
- Experience implementing MCP servers, MCP clients, or agent-to-tool integrations.
- Experience with multi-agent orchestration and frameworks such as LangGraph.
- Familiarity with vector databases such as Pinecone, Milvus, Weaviate, or FAISS.
- Experience with PostgreSQL, Redis, Kafka, or other data and messaging technologies.
- Experience deploying AI applications on AWS, Azure, or Google Cloud Platform.
- Knowledge of AI evaluation frameworks, observability, guardrails, and production tracing.
- Experience with network automation, cybersecurity, enterprise infrastructure, or Cisco-related technologies is a plus.
Education
Bachelor's or Master's degree in Computer Science, Software Engineering, or a related technical discipline, or equivalent practical experience.
Ideal Candidate Profile
The ideal candidate is a hands-on software engineer who combines strong Python development skills with Golang expertise and practical Agentic AI experience. Candidates should demonstrate experience building, integrating, testing, and deploying AI-powered applications in production environments—not just theoretical knowledge of LLMs or prompt engineering.