AI and Automation Engineer

Braviant Holdings•Dallas, TX

1d•Hybrid

About The Position

We are building out a new AI & Automation practice at Braviant and are hiring two AI and Automation Engineers to join the team. These are hands-on builder roles focused on designing, deploying, and governing AI-powered automation workflows across our business, spanning consumer lending originations, credit risk, compliance, collections, and internal operations. You will report to the Head of AI & Automation and work closely with stakeholders across the business to identify manual and semi-automated processes that can be replaced or accelerated by agentic AI workflows. Day-to-day, this means building agents that do real things: routing decisions, processing documents, triggering actions across systems, escalating exceptions to humans, and logging everything so we can audit and improve over time. This is a greenfield role at a company that uses Claude, Claude Code, and the broader Anthropic ecosystem as primary AI infrastructure. You will build on top of those tools and extend them. We are an AWS shop, and our preferred agentic framework is Strands Agents SDK, though we expect you to choose the right tool for the problem and bring framework judgment, not just framework familiarity. If you are early in your AI engineering career and want to own real production systems rather than prototype demos, and if you want to build in a regulated, high-stakes environment where the quality of your work actually matters, this role is for you.

Requirements

2 to 4 years of software engineering experience with production Python and SQL; additional languages a plus
Hands-on experience building and shipping AI/ML or LLM-powered solutions in real production environments, not just coursework or personal projects
Practical experience with at least one agentic or LLM orchestration framework (Strands, LangGraph, CrewAI, AutoGen, LlamaIndex, or similar)
Experience integrating AI services via APIs and building tool-use or function-calling patterns with LLMs
Familiarity with AWS and cloud-native architecture patterns
Active daily use of AI-assisted development tools such as Claude Code, VS Code with Cline, Cursor, GitHub Copilot, or similar
Experience with prompt engineering and structured outputs; comfort iterating on prompts as a core part of building
Strong written communication
Bachelor's degree in Computer Science, Engineering, or a related technical field, or equivalent practical experience

Nice To Haves

Direct experience with Amazon Bedrock, Bedrock AgentCore, or the Strands Agents SDK
Experience building or consuming MCP servers and clients
Familiarity with skills and plugin development for Claude, Microsoft Copilot, or similar AI platforms
Experience with OpenClaw, Hermes Agent, HyperAgent, or similar open-source agent frameworks
Familiarity with workflow automation platforms such as n8n, Zapier, Make, or similar
Background in fintech, consumer lending, payments, or another regulated financial services environment
Familiarity with RAG architectures, vector databases, or knowledge graph approaches
Working knowledge of application security fundamentals: auth, secrets management, RBAC, and audit logging
Familiarity with observability and evaluation practices for AI systems: logging, tracing, prompt evaluation, and model monitoring

Responsibilities

Design and build AI agent workflows that automate or accelerate business processes across originations, credit risk, compliance, collections, and operations
Migrate manual and semi-automated processes into governed, production-grade agent pipelines with appropriate human-in-the-loop checkpoints, approval gates, and escalation patterns
Build with Strands Agents SDK as the preferred default framework; apply judgment to use CrewAI, LangGraph, AutoGen, LlamaIndex, Haystack, or other frameworks where better suited
Implement structured outputs, function calling, and tool-use patterns to connect LLMs with internal business logic and data
Manage, build, and maintain MCP (Model Context Protocol) servers and clients to give agents structured, governed access to internal APIs, databases, and third-party data providers
Develop skills, plugins, and tool integrations for Claude and other AI platforms used across the organization
Integrate AI capabilities with existing systems via REST APIs, event queues, and cloud-native AWS services
Evaluate and implement lightweight automation connectors (n8n, Zapier, Make) for business stakeholder workflows where full agent development is not warranted
Instrument every workflow you build with logging, tracing, and alerting so teams can audit agent behavior, debug failures, and measure outcomes
Implement guardrails and usage controls across AI deployments, covering autonomous, semi-autonomous, ad hoc, scheduled, event-driven, manually triggered, and human-review-gated workflows
Contribute to responsible AI documentation including runbooks, incident response playbooks, and acceptable use standards for AI-assisted processes in a regulated fintech environment, in partnership with the Technology Operations team
Stay current on agentic AI developments, vulnerability patterns, and compliance requirements relevant to consumer lending
Work directly with business stakeholders to translate process requirements into agentic workflow specs
Contribute to shared frameworks, reusable agent components, and internal engineering standards developed by the Head of AI & Automation
Participate in design reviews, code reviews, and cross-team knowledge sharing