Agentic AI Architect - Intelligence Engineering (West)

About the role

At Slalom, we co-create modern technology and software products with clients who are ready to accelerate their digital product development. We imagine how things can be made better, then set out to realize what’s possible — driving innovation with quality, resilience, and purpose. By blending design, product engineering, analytics, and automation, we build the custom-built software and data products of tomorrow. As a member of Intelligence Engineering, you’ll design and deliver innovative AI/ML and agentic AI solutions as part of intelligent products and automating / re-envisioning human workflows on Amazon Web Services, Azure, and Google Cloud. This includes architecting multi-agent systems, LLM-powered autonomous workflows, retrieval-augmented generation (RAG) pipelines, and enterprise-grade AI governance frameworks using cutting-edge orchestration frameworks, tool-use protocols, and cloud-native AI services. You’ll help clients move from isolated proofs of concept to secure, scalable, observable systems that create real business value, while helping craft projects in their initial phases and delivering them with a team.

Responsibilities

• Provide thought leadership on AI/ML, Generative AI, and Agentic AI internally and with clients, while contributing to a culture of collaboration, learning, and curiosity
• Design end-to-end agentic AI architectures including planning loops, memory management, tool integration, and agent coordination patterns
• Architect multi-agent orchestration systems using frameworks such asStrands Agents SDK,OpenAI Agents SDK, Google ADK, Lang Graph or similar for autonomous reasoning, decision-making, and task execution
• Design and implement Model Context Protocol (MCP) server integrations for tool use, data access, and cross-system interoperability with enterprise systems
• Build advanced retrieval-augmented generation (RAG) systems including vector databases, embedding strategies, chunking optimization, hybrid search, re-ranking, and multi-source data synthesis
• Design and deliver AI and ML solutions across AWS, Azure, and GCP, using the right mix combination of cloud-native data services, ML tooling, LLM platforms, and software engineering practices
• Build in Python and, where useful, other languages to deliver machine learning systems, APIs, evaluation harnesses, retrieval pipelines, agent workflows, and production services
• Recommend and implement architecture for model and agent pipelines, CI/CD, testing, deployment, observability, andMLOps/LLMOps at scale
• Implement evaluation frameworks (e.g., RAGAS, DeepEval, LangSmith) to measure task success rates, tool-call accuracy, and reasoning integrity for GenAI systems
• Build guardrails for safety, compliance, and performance monitoring including human-in-the-loop (HITL) approval workflows, escalation policies, and sandbox isolation
• Define AI governance frameworks including model risk management, responsible AI practices, regulatory compliance, and authorization boundaries for autonomous decision-making
• Explain model and system behavior to both technical and non-technical audiences, including leading deep technical presentations, workshops, and architecture conversations
• Collaborate with Product Owners to apply Slalom’s agile process and lead the initiation, delivery, and transition of projects in a client-facing role
• Lead and mentor engineers and machine learning practitioners. Lead smaller projects (3 to 5 people) as the technical lead from project initiation to delivery
• Build trusted relationships with customers and collaborate across Slalom teams to share learnings and strengthen the broader Intelligence Engineering practice
• Will be delivery-focused approximately 85–95% of the time
• Willingness to travel up to 50%, at peak times

Qualifications

• 5+ years of software engineering experience building and deploying production systems; experience with machine learning, applied AI, or intelligent software systems is a plus, with 2+ years focused on generative AI, LLMs, or agentic AI systems
• Hands-on experience designing or building multi-agent systems including agent orchestration, tool integration, and autonomous decision-making workflows
• Proficiency with at least one agentic AI or workflow framework such as Lang Graph, Strands, AutoGen, CrewAI, Semantic Kernel, OpenAI Agents SDK, Google ADK, or similar
• Experience with RAG architectures including vector databases, embeddings, and retrieval optimization, and context management techniques such as chunking, summarization, and memory handling
• Experience developing production-ready solutions on at least one major cloud AI platform, such as AWS Bedrock, Azure AI Foundry/OpenAI Service, GCP Vertex AI/Gemini, or Databricks; experience operating and maintaining production environments is a plus
• Experience with AI-assisted development tools such as Claude Code, Cursor, Kiro, or similar IDE-based coding agents, including effective use for code generation, refactoring, debugging, and developer workflow acceleration
• Strong Python development skills; experience withFastAPI, Flask, or equivalent API frameworks
• Experience building ML or AI systems end to end, including data access, feature or retrieval flows, APIs, testing, deployment, and production support
• Familiarity with evaluation frameworks, tracing, observability, model behavior analysis, and regression testing for GenAI systems
• Understanding of prompt engineering, LLM fine-tuning, chain-of-thought reasoning, and structured output techniques
• Recognized as an authority on at least one technical domain (e.g., Agentic Systems, RAG, Multi-Agent Orchestration) with generalist familiarity across AI/ML techniques
• Ability to work across new domains and unfamiliar data structures and lead exploratory analysis when requirements are not fully defined
• Excellent verbal and written communication skills; ability to lead highly technical presentations
• Familiarity with Agile project delivery
• (Preferred) Experience with Model Context Protocol (MCP) server development and integration
• (Preferred) Experience with MLOps/LLMOps pipelines, CI/CD for ML, and model monitoring/observability

Pay

• East Bay, San Francisco, Silicon Valley: Senior Architect: $194,000-$237,000, Architect: $158,000-$194,000, Senior Engineer: $129,000-$157,000
• Los Angeles, Orange County, San Diego, Seattle: Senior Architect: $178,000-$218,000, Architect: $145,000-$177,000, Senior Engineer: $118,000-$144,000
• All other locations: Senior Architect: $163,000-$200,000, Architect: $133,000-$163,000, Senior Engineer: $108,000-$132,000

Schedule

Individuals may be eligible for an annual discretionary bonus. Actual compensation will depend upon an individual’s skills, experience, qualifications, location, and other relevant factors. The pay range is subject to change and may be modified at any time.