B

Bold Penguin

Operates API-driven commercial insurance marketplace

Senior Agentic AI Engineer

AI Application EngineeringPosted on Nov 16
Full-timeRemote in USA$130k - $155k /yr

About the Job

Requirements

  • Typically 5+ years of professional software engineering experience, with substantial backend or distributed-systems development experience.
  • Demonstrated hands-on experience building and deploying LLM-powered applications or AI agents in production or production-like environments.
  • Strong Python skills and experience designing maintainable services, APIs, and software components.
  • Practical experience with agent orchestration frameworks such as LangGraph, LangChain, or equivalent technologies.
  • Strong understanding of LLM capabilities and limitations, including prompting, tool calling, structured generation, context management, and model evaluation.
  • Experience designing REST APIs, integrating microservices, and working with asynchronous or event-driven systems.
  • Experience with RAG architectures, embeddings, semantic retrieval, and vector databases such as Pinecone, Weaviate, or pgvector.
  • Experience deploying cloud-based applications and using Docker, CI/CD, and infrastructure automation.
  • Understanding of production concerns including reliability, observability, performance, cost management, testing, and secure software development.
  • Ability to independently own a technical problem, communicate trade-offs, and deliver a working solution across the development lifecycle.
  • Must be able to sit, stand, and walk for prolonged periods of time, up to 8 hours per day, at a desk working on a computer.
  • Must be able to use standard office equipment for extended periods, including a mouse, keyboard, phone, and video conferencing.
  • Must be able to travel to the Bold Penguin office in Dublin, Ohio for new-hire onboarding and orientation for 2 days and 2 nights; travel costs are covered by Bold Penguin.
  • Must be able to travel occasionally, up to 10%, for corporate events and team planning sessions.

Responsibilities

  • Design and implement robust single-agent and multi-agent systems using patterns such as supervisor, planner, specialist agents, and delegated task execution.
  • Build agent workflows that support planning, tool use, state transitions, retries, checkpoints, resumability, and human-in-the-loop approvals.
  • Define clear boundaries between probabilistic agent reasoning and deterministic business rules, validations, and transaction execution.
  • Develop reusable agent capabilities, tools, prompts, workflow components, and orchestration patterns that can be adopted across products.
  • Manage agent context, memory, conversation state, task state, and long-running workflow lifecycle.
  • Integrate and evaluate foundation models from providers such as OpenAI, Anthropic, Google, and AWS Bedrock.
  • Engineer prompts, structured outputs, function/tool calling, context assembly, and model-routing strategies.
  • Build retrieval-augmented generation systems using embeddings, semantic search, metadata filtering, and vector databases.
  • Improve quality and reliability through grounding, validation, confidence-aware workflows, fallback strategies, and hallucination mitigation.
  • Optimize model selection, latency, throughput, token consumption, and inference cost without compromising business outcomes.
  • Integrate agents with enterprise APIs, microservices, data platforms, and business applications.
  • Build and consume Model Context Protocol servers and tools using secure, well-defined contracts.
  • Implement agent-to-agent communication and interoperability patterns, including task lifecycle, status, input, and result handling.
  • Design capability discovery, delegation, and invocation patterns for internal and external agents.
  • Create resilient integration patterns for asynchronous operations, streaming, event delivery, and external system failures.
  • Build scalable, fault-tolerant agent services using asynchronous and event-driven architectures.
  • Implement durable workflow execution, persistence, checkpointing, idempotency, retries, timeouts, and recovery from partial failures.
  • Establish observability across agent decisions, tool calls, traces, latency, token usage, costs, and business outcomes.
  • Develop automated testing and evaluation strategies for agent behavior, tool correctness, regression detection, and end-to-end workflows.
  • Implement enterprise security controls including authentication, authorization, tenant isolation, secrets management, auditability, and policy enforcement.
  • Deploy and operate services using cloud-native infrastructure, CI/CD, containers, and appropriate runtime platforms.
  • Lead technical design discussions and make pragmatic architecture decisions that balance speed, quality, scalability, and maintainability.
  • Partner with product, platform, security, and domain teams to translate business problems into agentic solutions with measurable outcomes.
  • Mentor engineers through design reviews, code reviews, pairing, and knowledge sharing.
  • Evaluate emerging agent frameworks, protocols, models, and tools; recommend adoption based on evidence rather than novelty.
  • Drive prototypes and proofs of concept into production-ready capabilities, including documentation and operational readiness.

Desired Qualifications

  • Experience designing multi-agent systems with supervisor, planner, worker, or specialist-agent patterns.
  • Hands-on experience implementing MCP servers, MCP clients, and tool integrations.
  • Experience with A2A or other agent interoperability protocols and distributed task lifecycle management.
  • Experience with AWS Bedrock, Bedrock AgentCore, or comparable managed model and agent runtime platforms.
  • Experience with agent memory, long-running workflows, state persistence, and human-in-the-loop interaction patterns.
  • Familiarity with agent tracing and evaluation tools such as LangSmith, as well as operational platforms such as Datadog or CloudWatch.
  • Knowledge of enterprise identity and security patterns, including OAuth 2.0, JWT, RBAC, and multi-tenant authorization.
  • Experience in insurance, financial services, healthcare, or another domain with complex workflows and compliance requirements.
  • Kubernetes experience.

About the Company

Bold Penguin

Operates API-driven commercial insurance marketplace

Bold Penguin runs the largest commercial insurance exchange that connects small businesses, insurance agents/brokers, and carriers to quotes quickly. It does not sell insurance directly; it provides a platform that helps agents and brokers find and secure coverage for clients. The platform uses an API-first, flexible, customizable technology to power both consumer and agent interfaces, coordinating connections and transactions among parties. Its goal is to create a smooth, efficient marketplace for commercial insurance that helps agents and brokers serve clients better and more profitably.

Company size
201-500
Company stage
Series B
Total funding
$33.5M
Headquarters
Columbus, OH
Founded
2016

Recently Posted Jobs

Explore more opportunities at Bold Penguin

See more jobs