AI Engineer

Location: San Jose, CA / Dallas, TX (Hybrid)

Client: iOPEX / Cisco

Job Description: Software Engineering & System DesignWrite, test, and deploy production-quality code with a strong focus on scalability and performance. Design and implement end-to-end systems including API, database, and application layers. Consider memory usage, performance optimization, and modular architecture in code design. Follow modern DevOps practices for deployment and environment management.

Python Development: Write clean, modular Python code with proper environment management (virtualenv, poetry, conda).Build and deploy RESTful APIs using frameworks like FastAPI or Flask. Connect applications to relational and NoSQL databases. Containerize applications using Docker and deploy in Kubernetes / cloud environments. Database SkillsWrite and optimize SQL and PL/SQL queries for data retrieval and transformation. Integrate database logic effectively into application workflows.

Generative AI Development: Understand how Large Language Models (LLMs) work - architecture, limitations, and tuning methods. Design and implement RAG (Retrieval-Augmented Generation) systems: Build pipelines connecting vector databases, LLMs, and application layers. Optimize retrieval and response accuracy through prompt engineering and context management. Apply best practices and advanced RAG techniques (chunking strategies, caching, query re-ranking).Develop and manage prompt templates, parameter configurations, and evaluation metrics.

Agentic AI Systems: Understand AI agents, their lifecycle, and how they integrate with tools and APIs. Implement tool calling and human-in-the-loop workflows. Design multi-agent architectures using frameworks such as LangChain or LangGraph. Apply agent orchestration best practices, ensuring reliability, observability, and control.

Required Skills & Qualifications: Strong understanding of software design principles and ability to think like a developer (language agnostic).Proficiency in Python with good exposure to building APIs, database integration, and container-based deployment. Working knowledge of SQL / PL-SQL for querying and joining data. Experience in developing or integrating GenAI or RAG-based systems using OpenAI, Anthropic, or similar models. Familiarity with LangChain, LangGraph, or similar frameworks for AI workflow orchestration. Strong debugging, optimization, and analytical skills. Excellent communication and collaboration abilities in a fast-paced environment.

Nice to Have: Exposure to cloud platforms (AWS, GCP, Azure) for AI workload deployment. Experience with vector databases (FAISS, Pinecone, Weaviate, or Chroma).Knowledge of monitoring and observability tools for AI systems. Familiarity with CI/CD pipelines, GitOps, and infrastructure automation.