Software Engineer – AI Agents & Intelligent Systems

Role Overview
We are seeking a highly skilled Software Engineer with deep expertise in AI-enabled application development, agentic systems, and modern cloud engineering to join our growing engineering organization in the Bay Area.
This role is focused on building enterprise-grade intelligent systems powered by Large Language Models (LLMs), advanced Retrieval-Augmented Generation (RAG), and autonomous AI agents. The ideal candidate combines strong software engineering fundamentals with hands-on experience designing scalable AI architectures, deterministic agent workflows, and evaluation frameworks for production environments.
You will work across engineering, product, platform, and AI research teams to design next-generation AI-enabled enterprise solutions at scale.

• Design and build enterprise-grade AI agents and agentic workflows using modern LLM frameworks
• Develop deterministic and controllable agent architectures for production reliability
• Implement agent skills, orchestration logic, memory strategies, and tool integrations
• Engineer prompt architectures and prompt optimization strategies for complex enterprise use cases
• Build scalable multi-agent systems with strong observability and governance controls

• Develop advanced RAG (Retrieval-Augmented Generation) pipelines
• Optimize context management, token usage, and progressive disclosure strategies
• Build semantic retrieval and contextual ranking solutions
• Design knowledge ingestion and vectorization workflows
• Improve response quality, latency, and grounding accuracy for enterprise AI systems

• Develop scalable backend services using Python
• Build and integrate RESTful APIs and distributed service connections
• Work extensively with JSON-based data models and API contracts
• Contribute to open-source initiatives and maintain strong GitHub engineering practices
• Implement secure, scalable, and observable microservices architectures

• Build automated evaluation frameworks for LLM and agent performance
• Design testing and validation methodologies for AI agents
• Implement regression testing, benchmarking, hallucination detection, and output quality scoring
• Improve reliability, determinism, and operational safety of AI systems
• Establish CI/CD quality gates for AI-enabled applications

• Deploy and operate AI workloads on Google Cloud Platform (GCP)
• Work with enterprise cloud engineering and platform teams to operationalize AI solutions
• Optimize scalability, reliability, and cost efficiency across cloud-native systems
• Support platform integration initiatives including GECX and enterprise AI ecosystems

• Bachelor’s or Master’s degree in Computer Science, Engineering, or related field
• 5+ years of software engineering experience
• Strong programming expertise in Python
• Experience building scalable APIs and distributed systems
• Strong understanding of JSON, API integrations, and backend architectures
• Hands-on experience with LLMs and generative AI application development
• Experience designing and building AI agents or agentic systems
• Experience with prompt engineering and context optimization techniques
• Experience building advanced RAG pipelines
• Familiarity with automated AI evaluation and testing frameworks
• Experience deploying solutions on GCP
• Strong GitHub and open-source development practices

• Experience with multi-agent orchestration frameworks
• Experience with vector databases and semantic search
• Familiarity with LangChain, LangGraph, LlamaIndex, CrewAI, AutoGen, or similar frameworks
• Experience implementing deterministic workflows and guardrails for AI systems
• Exposure to enterprise compliance, governance, and responsible AI practices
• Experience with observability, telemetry, and AI system monitoring
• Experience operating large-scale enterprise AI platforms

• Python
• APIs & Service Integration
• JSON
• GitHub & Open Source Development
• Distributed Systems

• Agentic Coding & Agent Building
• Prompt Engineering
• Deterministic Agent Design
• Agent Skills & Tooling
• Multi-Agent Systems

• Large Language Models (LLMs)
• Advanced RAG
• Context Optimization
• Progressive Disclosure
• Knowledge Retrieval Architectures

• Automated Evaluation Frameworks
• Agent Testing & Validation
• AI Reliability Engineering
• Benchmarking & Regression Testing

• Google Cloud Platform (GCP)
• Enterprise AI Platforms
• GECX
• CI/CD & Cloud-Native Engineering