taxbit

Agentic AI Engineer

Salt Lake City, Utah$130k–$170kmidAdded today

About this role

Taxbit seeks an Agentic AI Engineer to design and deploy autonomous AI systems that simplify tax and compliance workflows for enterprise customers. You'll build production-grade agentic applications using AWS services, handling the full lifecycle from prompt engineering to monitoring and iteration in a high-stakes financial environment.

What you'll do

Design and deploy customer-facing agentic AI products using AWS Bedrock, Strands Agents, AgentCore, and Lambda
Architect multi-agent systems with reliable tool use, memory management, and orchestration patterns for financial accuracy
Own AI feature lifecycle from prompt engineering and agent design through evaluation, deployment, and production monitoring
Partner with product and customer success teams to translate user problems into production-grade AI solutions
Write well-tested, maintainable code and participate in code reviews to distribute AI/ML knowledge across the team
Collaborate with engineers, data teams, and compliance stakeholders to ensure AI outputs meet regulatory standards

What they're looking for

Python and/or TypeScript development
AWS AI/ML services (Bedrock, Strands, AgentCore, SageMaker, Lambda)
Agentic AI patterns (tool use, RAG, memory management, multi-agent orchestration)
LLM pipeline design, prompt engineering, and hallucination mitigation
AI observability, evaluation frameworks, and responsible AI practices
AWS cloud infrastructure, IAM, and CI/CD (DataDog, GitHub)
Production AI/LLM application shipping experience
Agile methodologies and cross-functional communication

Benefits

Competitive salary ($130K–$170K) plus equity (RSUs) and incentive compensation
Comprehensive benefits package and modern 401(k) with crypto and financial wellness options
Hybrid work: 3 days in-office, 2 days flexible/remote in Salt Lake City
Discretionary time off, paid parental leave, and fertility benefits
Team lunches, snacks, and autonomous work culture

Likely interview questions

Walk us through a production LLM or agentic system you built—what were the key design decisions around tool use, memory, and reliability?
How have you approached prompt engineering and evaluation in a domain where accuracy and compliance matter?

Describe your experience mitigating hallucinations and ensuring trustworthy outputs in financial or regulated contexts.
Tell us about a time you shipped an AI feature end-to-end and had to iterate based on real user behavior or feedback.
How do you stay current with rapidly evolving AI research and tooling, and how have you brought new ideas to a team?
What's your experience with AWS Bedrock, Strands, or similar agentic frameworks, and how would you approach architecting a multi-agent system?
How do you balance shipping quickly with maintaining code quality and observability in production AI systems?

Unlock all 7 questions free — and practice them live →

Apply on the employer's site →

Opens the official application on the employer’s site. No login required.