• Design and evolve conversational agents in production at high volume, with WhatsApp as the primary channel • Orchestrate multi-agent systems: intent routing, handoff, session management, memory and failure recovery • Develop tools and MCP servers that connect agents to the business domain • Instrument LLM observability (Langfuse / LangSmith / OpenTelemetry): cost, latency, tool-call rate and production quality • Build and maintain automated evals — no prompt or model change goes live without measurement • Integrate multiple LLM providers (OpenAI, Anthropic, Groq) with fallback strategies and cost controls • Implement RAG pipelines (embeddings, pgvector, reindexing) • Create and maintain Claude Code skills, subagents and workflows that automate the delivery cycle • Ensure reliability: rate limiting, durable queues, anti-bot guardrails, error tracking • Operate agents on Kubernetes: GitOps deployments, resources, metrics and manifests • Collaborate with product and design during discovery

• Own the AI-native architecture and build it. • Own AI/MLOps and AI telemetry end-to-end. • Lead the AI practice from the front.

Role Description - 6-8 years of hands-on experience with Generative AI, AI, ML, and Data Science technologies - Extensive hands-on experience in implementing end-to-end projects utilizing Generative AI - Experience in building production-grade solutions utilizing Generative AI as well as AI and ML components - Extensive hands-on experience in building Generative AI applications using methodologies such as RAG, prompt engineering, embedding, fine-tuning, etc. - Experience in working with structured as well as unstructured data for building RAG-based solutions - Experience with AI/ML search and data services within GCP ecosystem such as GCP Vertex AI, Vertex AI Vector Search, Gemini, Cloud Run, Cloud SQL, etc. - Experience with agent frameworks such as Google ADK, Langgraph, CrewAI, etc. - Hands-on experience in working with cloud AI services GCP Vertex AI, Azure AI, AWS Bedrock, as well as managed large language models (Preferred GCP but other cloud experience can be considered) - Extensive experience in Python programming languages along with popular frameworks such as Flask, FastAPI, etc. - Experience with AIML, deep learning, TensorFlow, Python, NLP - Excellent understanding of Generative AI related concepts, methodologies, and techniques Qualifications - Bachelor's degree in computer science or related field - 5 years AIML experience including 2 years in GenAI projects - Proficiency with Azure AI services, Python - Experience with agent-based frameworks LangChain, LangGraph is highly desirable - Solid understanding of API integration, test automation, and software engineering principles - Good teamwork and communication skills Requirements - Mandatory Skills: MLOPS, GenAI - LLMOps, Machine Learning - AIOPS

Role Description CAI is hiring a Senior Applied AI Architect to serve as the primary technical engine behind our applied AI delivery across all four strategic motions. This is a builder’s role at the intersection of deep technical execution and strategic advisory. What You'll Do - Lead technical design for agentic AI systems, LLM integrations, MCP-based orchestration, and multi-model workflows in internal and external delivery environments. - Own build-vs-buy decisions for AI tooling across use cases, working with the CTO organization and design partners. - Develop reusable architectural patterns, integration blueprints, and technical playbooks that scale across CAI’s delivery organization. - Drive technical POC development from internal initiatives through to client-ready case studies, architecture and implementation. - Serve as the technical lead and credibility anchor for AI solution conversations with executives, clients, and procurement stakeholders. - Work alongside functional and motion owners to determine whether and how AI applies, then own the technical approach and execution. - Pressure-test AI feasibility on CTO assessments, POC scoping, and motion-level AI roadmaps. - Mentor and develop junior AI technical staff; contribute to the Applied AI Delivery Team model. - Maintain deep, working knowledge of the enterprise AI landscape: LLMs (Anthropic Claude, OpenAI, Gemini), agentic frameworks, MCP architecture, Databricks, vector databases, and emerging tools. - Apply hands-on fluency across the full stack CAI deploys; AI/ML frameworks, integration patterns, API design, cloud platforms (AWS, Azure), and security controls relevant to commercial and public sector. - Ensure architectural choices align with CAI’s governance standards, NIST AI framework, GovRAMP requirements, and client-specific compliance environments. - Bring an evidence-based perspective on AI capability and limitations to keep initiatives grounded, realistic, and defensible. - Package internal AI delivery results into reusable inputs for client-ready case studies, RFP content, and competitive positioning. - Build the technical artifacts that move work forward: solution designs, architecture diagrams, integration specs, feasibility assessments, and deployment guides. Qualifications - 8-10+ years of experience in applied AI, enterprise software architecture, or AI/ML engineering with at least 3 years in a senior or lead role. - Demonstrated track record of designing and delivering production-grade AI solutions end-to-end; hands-on, not advisory. - Deep fluency with large language models, agentic AI frameworks, prompt engineering, and MCP or similar orchestration architectures. - Hands-on experience with enterprise AI platforms: Anthropic Claude, OpenAI, Databricks, Azure AI / OpenAI Service, AWS Bedrock, or equivalent. - Strong system design and integration architecture skills: APIs, data pipelines, event-driven systems, and cloud infrastructure. - Ability to operate credibly across technical depth (code environments, architecture review) and executive conversation. - Experience working in regulated or government-adjacent environments, with familiarity with FedRAMP, GovRAMP, NIST, or SOC 2 compliance requirements. - Strong communication skills: able to translate complex technical architecture into executive-ready artifacts and client-facing narratives. - Bachelor's degree in computer science, Engineering, or a related technical field required; master's or advanced degree preferred; or the equivalent combination of education, technical certifications or training, or work experience. Requirements - Experience delivering AI solutions in state and local government, public sector managed services, or workforce services environments. - Hands-on experience with Anthropic’s Model Context Protocol (MCP) and multi-agent orchestration frameworks (LangChain, AutoGen, CrewAI, or equivalent). - Track record of building reusable AI architectural assets, patterns, blueprints, frameworks, that scale beyond a single engagement. - Experience contributing to AI governance frameworks, responsible AI posture, or client-facing compliance advisory. - Certifications in relevant platforms (AWS, Azure, Databricks, Google Cloud AI) or AI governance frameworks (ISACA, NIST AI RMF). - Prior experience in a professional services or consulting delivery model with multiple concurrent client engagements. Physical Demands - Ability to safely and successfully perform the essential job functions consistent with the ADA and other federal, state, and local standards. - Sedentary work that involves sitting or remaining stationary most of the time with occasional need to move around the office to attend meetings, etc. - Ability to conduct repetitive tasks on a computer, utilizing a mouse, keyboard, and monitor. Reasonable Accommodation Statement If you require a reasonable accommodation in completing this application, interviewing, completing any pre-employment testing, or otherwise participating in the employment selection process, please direct your inquiries to application.accommodations@cai.io or (888) 824 – 8111. EEO Statement It is the policy of Computer Aid, Inc.(CAI) not to discriminate against any employee or applicant for employment because of race, color, religion, sex, sexual orientation, gender identity, national origin, age, marital status, genetic information, disability or because he or she is a protected veteran. It is also the policy of CAI to take affirmative action to employ and to advance in employment, all persons regardless of race, color, religion, sex, sexual orientation, gender identity, national origin, age, marital status, genetic information, disability or protected veteran status, and to base all employment decisions only on valid job requirements.