AI Solutions Engineer Agentic AI & Multi-Agent Systems

We are looking for a hands-on AI Solutions Engineer Agentic AI & Multi-Agent Systems to join our technical team and help build advanced AI-powered business systems.

This role is for someone who has moved beyond basic LLM integrations and has practical experience building AI agents, agentic workflows, tool-calling systems, or multi-agent applications.

You will work with our existing AI/software team to build AI systems that can understand business goals, plan tasks, use tools and APIs, coordinate specialized agents, review outputs, and execute approved actions.

This is not a basic chatbot, simple RAG, prompt-engineering, or Zapier/Make automation role.

What We Are Building

We are working toward an AI Manager that can:

Understand business goals, SOPs, policies, and business knowledgeAccess authorized business dataAnalyze business situationsBreak objectives into smaller tasksPlan and coordinate tasks across AI agentsUse approved tools, APIs, and business systemsReview and validate AI-generated outputsIdentify uncertainty or conflicting informationRequest human approval for high-risk actionsExecute approved actionsVerify results after executionMaintain memory and task stateMaintain logs and decision historyHandle failures, retries, and incomplete tasksPotential agents may include:

Research AgentAnalyst AgentSEO AgentMarketing AgentProduct AgentOperations AgentExecution AgentReview/Critic AgentThe final architecture is not fixed. We expect you to contribute ideas and help determine where agents, workflows, APIs, and deterministic logic should be used.

Key Responsibilities

Agentic AI Development

Build and improve AI agents and agentic workflows.Develop multi-step task-planning and execution flows.Implement LLM tool/function calling.Build agents that interact with APIs and external systems.Develop agent memory, state, and context-management mechanisms.Implement agent review/validation workflows.Multi-Agent Systems

Work with multiple specialized agents and orchestration workflows.Implement communication and context-sharing between agents.Handle retries, failures, conflicting outputs, and incomplete tasks.Experiment with different orchestration approaches and recommend practical solutions.APIs & Tools

Connect AI agents with APIs and business tools.Implement secure tool-calling mechanisms.Work with structured inputs/outputs and function calling.Ensure AI-generated actions are validated before execution.AI Security & Reliability

Implement basic security controls around AI agents and tools.Understand prompt injection and unauthorized-action risks.Apply permission-based access to tools and data.Support human approval workflows for sensitive actions.Maintain logs and traces of important agent activities.Evaluation & Observability

Test AI agents for accuracy, reliability, and task completion.Track agent failures and tool-call errors.Support monitoring, logging, tracing, and evaluation of agent workflows.Improve workflows based on real-world performance.Technical Collaboration

Work closely with AI and software engineers.Convert business requirements into technical solutions.Participate in architecture discussions and code reviews.Create technical documentation and workflow diagrams.Help move AI prototypes toward reliable production systems.Required Skills

Candidates should have hands-on experience with:

Agentic AI / AI AgentsMulti-Agent Systems or Agent OrchestrationGenerative AI / LLMsPythonLLM APIsFunction Calling / Tool CallingAPI IntegrationAI Workflow DevelopmentMemory / State ManagementBasic AI SecurityAI Evaluation and DebuggingPreferred Technologies

Experience with one or more:

LangGraphLangChainMCPOpenAI APIs / AgentsAnthropic APIsPythonFastAPIVector DatabasesDockerAWS / GCP / AzureEvent-driven architecturesFramework expertise is not mandatory. We care more about practical understanding and hands-on implementation.

Production Experience Required

Candidates should have personally built real AI agent or agentic workflow projects.

Your application should ideally include:

Project/company/client name, where disclosure is permittedWhat the AI system actually didProduction / POC / prototype statusYour personal contributionTechnologies usedNumber of agents/workflows involvedArchitecture or workflow diagram, if availableGitHub, demo, Loom, screenshots, or case study, if availableConfidential information does not need to be shared. Anonymized examples are acceptable.

Not a Good Fit If Your Experience Is Mainly

Basic ChatGPT integrationsSimple OpenAI API callsBasic RAG chatbotsPrompt engineering onlyZapier/Make automationAI content generationBasic AI assistantsTutorial projectsAcademic projectsProjects that were only copied from tutorialsNo hands-on coding experienceWhat We Expect

You should be able to practically explain:

How would you build an AI agent that can use tools and APIs When should you use a single agent vs multiple agents How should multiple agents share information How should agent