AI / Agent Engineer

ROLE OVERVIEW

We are looking for a skilled AI / Agent Engineer to build, integrate, and operate intelligent agentic systems that power automation and AI-driven experiences across our fintech platform. You will work within a cross-functional AI Pod, developing agent workflows, integrating LaunchDarkly for feature management, and ensuring robust observability across all AI systems. You will collaborate closely with architects and senior engineers to deliver high-quality agentic solutions.

KEY RESPONSIBILITIES

• • Design, develop, and deploy AI Agent workflows using LLM-based orchestration frameworks (LangChain, AutoGen, CrewAI, or similar).
    • Integrate LaunchDarkly for feature flagging, progressive rollouts, and experimentation across AI-enabled features.
    • Implement comprehensive telemetry, logging, distributed tracing, and monitoring for AI agent systems.
    • Build and maintain A/B testing and experimentation frameworks to evaluate agent performance and model outputs.
    • Develop REST and event-driven integrations to connect AI agents with enterprise data sources and downstream systems.
    • Author technical documentation including agent design specs, integration guides, and architecture deliverables.
    • Participate in sprint ceremonies, contribute to backlog grooming, and deliver iteratively within an Agile framework.
    • Support incident response, root-cause analysis, and continuous improvement for production AI systems.

REQUIRED SKILLS & EXPERIENCE

• • 8+ years of software engineering experience with at least 1+ year(s) focused on AI/ML or agentic systems.
    • Proficiency in Python (primary) and familiarity with TypeScript or Java for integration layers.
    • Hands-on experience developing AI Agents using LangChain, AutoGen, CrewAI, or comparable frameworks.
    • Working knowledge of LaunchDarkly or equivalent feature flagging / experimentation platforms.
    • Experience implementing observability stacks: OpenTelemetry, Datadog, Grafana, Prometheus, or similar.
    • Understanding of LLM APIs (OpenAI, Anthropic, Azure OpenAI) and prompt engineering best practices.
    • Familiarity with cloud platforms (AWS, Azure, or GCP) and containerized deployments (Docker, Kubernetes).
    • Strong communication skills with the ability to produce clear technical documentation.

PREFERRED QUALIFICATIONS

• • Experience in financial services, banking, or fintech environments.
    • Exposure to vector databases (Pinecone, Weaviate, pgvector) and RAG (Retrieval-Augmented Generation) architectures.
    • Exposure to CI/CD pipelines and DevOps practices for ML or AI systems.
    • Familiarity with responsible AI principles, bias testing, and model evaluation frameworks.