Site Reliability Engineer II (Python, Panda, GenAI)

• Design, deploy, and maintain highly available RAG pipelines including vector databases, embedding services, and LLM inference infrastructure
• Ensure reliable operation of agentic AI systems including multi-agent orchestration platforms, tool integration frameworks, and decision-making workflows
• Implement comprehensive monitoring and observability for AI model performance, token usage, latency, and accuracy metrics
• Lead incident response for AI system outages, including model degradation, vector search failures, and agent execution issues

• Optimize and maintain vector database infrastructure (Pinecone, Weaviate, Chroma, or similar) for high-performance similarity search at scale
• Manage embedding model deployments and ensure consistent document ingestion pipelines with proper chunking and preprocessing
• Implement retrieval quality monitoring, including relevance scoring and context window optimization
• Design and maintain hybrid search systems combining vector and traditional search methodologies

• Build and maintain infrastructure for autonomous agent systems including planning, reasoning, and tool execution frameworks
• Implement robust error handling and fallback mechanisms for agent decision chains and multi-step workflows
• Monitor and optimize agent performance metrics including success rates, execution time, and resource utilization
• Ensure secure and reliable integration between agents and external APIs, databases, and services

• Develop Infrastructure as Code solutions for AI/ML workloads including GPU clusters, model serving infrastructure, and data pipelines
• Build automated deployment pipelines for LLM fine-tuning, RAG system updates, and agent workflow modifications
• Implement A/B testing frameworks for AI system improvements and model version management
• Design capacity planning and auto-scaling solutions for variable AI workloads and inference demands

• 5+ years of SRE/DevOps experience with 2+ years specifically focused on AI/ML production systems
• Deep hands-on experience with RAG architecture implementation including vector databases, embedding models, and retrieval systems
• Proven experience with agentic AI frameworks (LangChain, LlamaIndex, AutoGPT, CrewAI, or similar) and multi-agent orchestration
• Strong understanding of LLM deployment and optimization including model serving frameworks (vLLM, TensorRT-LLM, Triton) and GPU infrastructure management

• Proficiency with vector database technologies (PgVector, Pinecone, Weaviate, Qdrant, Chroma, Milvus) and their operational requirements
• Experience with embedding models (OpenAI, Sentence Transformers, Cohere) and semantic search optimization
• Knowledge of hybrid search implementations combining vector, keyword, and graph-based retrieval methods
• Understanding of chunking strategies, document preprocessing, and knowledge graph integration

• Experience implementing AI-specific monitoring including model drift detection, hallucination tracking, and response quality metrics
• Proficiency with MLOps tools (MLflow, Weights & Biases, Neptune) and experiment tracking systems
• Knowledge of AI system debugging including prompt tracing, agent execution visualization, and performance bottleneck identification
• Understanding of AI safety monitoring including content filtering, bias detection, and usage pattern analysis

• Proficiency with cloud AI services (AWS SageMaker, Google Vertex AI, Azure ML) and their operational aspects

• Advanced Kubernetes experience including GPU scheduling, resource quotas, and AI workload optimization
• Experience with container technologies optimized for ML workloads and model serving

• Proficient in Python with deep understanding of AI/ML libraries (transformers, langchain, llamaindex, torch, numpy)
• Experience with Infrastructure as Code tools (Terraform, Helm) specifically for AI infrastructure provisioning
• Strong API design and integration skills for AI service orchestration and tool integration
• Knowledge of streaming and async processing for real-time AI applications

• Production experience with document ingestion pipelines, chunking strategies, and metadata management
• Understanding of retrieval quality optimization including re-ranking, query expansion, and context selection
• Experience with multi-modal RAG systems incorporating text, images, and structured data
• Knowledge of RAG evaluation frameworks and automated quality assessment

• Hands-on experience with agent planning algorithms, tool selection mechanisms, and execution engines
• Understanding of multi-agent coordination, communication protocols, and distributed agent systems
• Experience with agent memory systems, state management, and long-running workflow orchestration
• Knowledge of agent safety mechanisms including execution sandboxing and output validation

• Experience with fine-tuning and RLHF (Reinforcement Learning from Human Feedback) infrastructure
• Knowledge of edge AI deployment and model optimization techniques
• Familiarity with AI governance, compliance frameworks, and ethical AI implementation
• Experience with conversational AI platforms and dialogue management systems
• Understanding of knowledge graphs and symbolic reasoning integration with neural systems

• Competitive base salaries
• Bonus incentives
• Support for financial-well-being and retirement
• Comprehensive medical, dental, vision, life insurance, and disability benefits (depending on location)
• Flexible working model with hybrid, onsite or virtual arrangements depending on role and business need
• Generous paid parental leave policies (depending on your location)
• Free access to global on-site wellness centers staffed with nurses and doctors (depending on location)
• Free and confidential counseling support through our Healthy Minds program
• Career development and training opportunities

American Express