Agentic AI Senior Consultant

Accountabilities:

Own the technical success of enterprise customers' agentic AI initiatives, managing the complete delivery lifecycle from initial discovery and solution design through development, production deployment, ongoing operations, and advisory services.
Lead customer workshops to identify, assess, and prioritize high-value agentic AI use cases, translating business objectives into measurable and technically achievable workflows.
Design and implement sophisticated multi-agent architectures, including agent decomposition, orchestration, task delegation, tool integration, memory management, state handling, and human-in-the-loop controls.
Develop, review, and troubleshoot production-quality software using Go or Python, building agents, plugins, tools, and integrations that meet enterprise requirements.
Deploy and operate agentic AI applications using Docker, Kubernetes, and major cloud platforms, ensuring scalability, reliability, and maintainability.
Integrate AI agents with enterprise applications, data sources, and legacy systems through MCP servers, A2A protocols, REST APIs, and event-driven messaging architectures.
Implement retrieval-augmented generation (RAG), vector databases, knowledge bases, embeddings, and real-time event context strategies to improve agent accuracy and access to relevant information.
Apply the Agent Development Lifecycle (ADLC) throughout solution delivery, covering requirements gathering, architecture design, evaluation pipelines, testing, version control, release management, monitoring, and operational documentation.
Establish robust observability, security controls, governance frameworks, and responsible AI practices for agentic systems, including tracing, quality evaluation, cost and latency monitoring, access control, and auditability.
Advise customers on large language model selection and optimization across providers such as Anthropic, OpenAI, Google, AWS Bedrock, and Azure AI Foundry, considering prompt engineering, token consumption, costs, and model performance trade-offs.
Act as a long-term technical advisor, identifying opportunities for further AI adoption and helping customers progress from isolated pilots to enterprise-wide, event-driven AI implementations.
Conduct recurring technical reviews, solution health checks, and roadmap discussions aligned with customer priorities and annual planning cycles.
Enable customer engineering teams to independently operate, maintain, and extend implemented solutions through technical workshops, collaborative development sessions, and comprehensive documentation.
Develop reusable technical assets, including reference architectures, implementation patterns, accelerators, and best practices, to improve delivery efficiency and consistency across future engagements.
Represent customer needs and technical feedback to internal Product and Engineering teams, contributing insights that influence product development and roadmap priorities.
Collaborate closely with agentic AI platform engineering teams to resolve complex customer challenges, validate new capabilities, and contribute reusable agents, plugins, and accelerators.
Provide technical leadership and mentorship to other professionals, helping strengthen agentic AI expertise and delivery capabilities across the Professional Services organization.
Communicate complex technical concepts, AI-related risks, and architectural trade-offs clearly to both technical and non-technical stakeholders.
Travel when required to support customer engagements, including occasional international travel.
Requirements:
At least 7 years of professional experience in professional services, technology consulting, systems integration, forward-deployed engineering, or enterprise application development.
Minimum 2 years of hands-on experience designing, developing, and deploying LLM-based applications and agentic AI solutions, including at least one solution successfully taken into production.
Strong understanding of software development lifecycle (SDLC) practices, including version control, automated testing, CI/CD, and release management, with practical experience applying a structured Agent Development Lifecycle (ADLC).
Strong programming proficiency in Go or Python, with Go considered a significant advantage.
Practical experience designing and implementing multi-agent systems, including task delegation, orchestration, coordination, and autonomous decision-making.
Familiarity with agent development frameworks such as Google ADK, LangGraph, LangChain, CrewAI, or comparable technologies.
Experience with agent interoperability and tool integration, including Model Context Protocol (MCP), Agent-to-Agent (A2A) protocols, and designing APIs for agent-based applications.
Solid understanding of retrieval-augmented generation (RAG), embeddings, vector databases, prompt engineering, and context management techniques.
Experience implementing evaluation frameworks, observability solutions, and security guardrails for enterprise LLM applications.
Strong knowledge of event-driven architectures, asynchronous messaging, distributed systems, and enterprise integration patterns.
Hands-on experience deploying distributed applications on cloud platforms such as AWS, Microsoft Azure, or Google Cloud Platform, using Docker and Kubernetes.
Understanding of enterprise security and identity management practices relevant to AI systems, including OAuth 2.0, role-based access control (RBAC), secrets management, and data privacy.
Ability to independently lead customer engagements, make sound technical decisions, and manage complex projects with minimal supervision.
Excellent written and verbal communication skills, including experience facilitating technical workshops and presenting recommendations to senior stakeholders.
Professional fluency in English and either Spanish or Italian, both written and spoken.
Experience working with agentic AI platforms or enterprise messaging technologies is highly desirable.
Familiarity with Solace Agent Mesh or similar agentic AI platforms is a plus.
Proficiency in both Go and Python is an additional advantage.
Experience with messaging technologies such as Solace, Kafka, RabbitMQ, ActiveMQ, IBM MQ, or TIBCO is beneficial.
Working knowledge of LLM platforms and services, including Anthropic Claude, OpenAI, Google Gemini/Vertex AI, AWS Bedrock, or Azure AI Foundry, is desirable.
Familiarity with LLMOps or MLOps practices, including prompt and model versioning, evaluation frameworks, and production monitoring, is a plus.
Knowledge of AI governance, responsible AI frameworks, and regulatory requirements in industries such as financial services, healthcare, or the public sector is advantageous.
Experience using AI-assisted and agentic coding tools such as Claude Code, Cursor, or GitHub Copilot, including the ability to demonstrate and share these practices with others.
Familiarity with MQTT, AMQP, REST APIs, and enterprise integration architectures is beneficial.
Relevant certifications, such as AWS Certified Machine Learning or Generative AI, Azure AI Engineer Associate, or Google Professional Machine Learning Engineer, are considered an advantage.
Previous experience creating technical workshops, reference architectures, blogs, presentations, or demonstrations focused on agentic AI is a plus.
Benefits:
Competitive compensation: Attractive remuneration package aligned with your skills and professional experience.
Flexible working arrangements: Remote-first and hybrid working options designed to support different working preferences and locations.
Work-life balance: A flexible working culture that encourages employees to maintain a healthy balance between professional and personal commitments.
Professional development: Access to training programs and continuous learning opportunities to strengthen technical and consulting expertise.
Career growth: Opportunities to develop your career while working on advanced enterprise AI implementations.
Innovative projects: Direct involvement in cutting-edge agentic AI, event-driven architecture, and enterprise digital transformation initiatives.
Expert collaboration: Opportunity to work alongside highly skilled professionals and leading technical experts in AI and software engineering.
Customer impact: Exposure to major international enterprise customers and complex, high-value technology challenges.
Values-driven culture: An environment built around craftsmanship, trust, courage, freedom, momentum, humility, and a strong focus on human experience.
Collaborative environment: A supportive workplace that encourages knowledge sharing, teamwork, creativity, and continuous improvement.
Employee engagement: Opportunities to participate in social activities, team initiatives, and creative projects.
International exposure: Collaboration with customers and colleagues across different countries and industries.
Technical ownership: Significant autonomy to influence customer architecture decisions, contribute to product evolution, and shape enterprise AI adoption.