Agentic AI Engineer

About the role

This role focuses on developing intelligent, customer-facing AI products within the FinTech sector. The work involves using AWS-native technologies like Strands Agents, AgentCore, Bedrock, and Lambda to create systems that redefine tax and compliance workflows. A key aspect is architecting reliable multi-agent systems with effective tool use, memory, and orchestration patterns to ensure accuracy in financial contexts.

The engineer will own the complete lifecycle of AI features, from initial prompt engineering and agent design through evaluation, deployment, and ongoing monitoring. This includes writing well-designed, maintainable code and participating in code reviews to ensure quality. Success in this position means rapidly iterating on systems based on user feedback and behavior, while ensuring AI outputs meet strict accuracy and regulatory standards.

Collaboration is central to this role, requiring partnerships with product managers and customer success teams to understand user needs deeply. The engineer will also work cross-functionally with other engineering teams, data specialists, and compliance stakeholders. The goal is to translate complex user problems into elegant, production-grade AI solutions that support TaxBit's mission of automating global tax reporting for the digital economy.

The compensation for this role ranges from $130,000 to $170,000 annually, in addition to equity.

Skills that matter here

• AWS: This role will design and deploy AI products using AWS-native technologies including Strands Agents, AgentCore, Bedrock, and Lambda.
• Python: The engineer will write well-designed and maintainable code, likely utilizing Python for AI/ML development.
• TypeScript: This role involves building customer-facing products, suggesting TypeScript could be used for front-end or full-stack development.

Who this role suits

• A person who thrives on translating complex user problems into practical, production-grade AI solutions.
• Someone with a strong understanding of agentic AI patterns, including tool use, RAG, and multi-agent orchestration.
• An individual who can work effectively in an agile environment and communicate intricate AI concepts to diverse audiences.
• A candidate who is meticulous about code quality, testing, and monitoring AI systems in production.

From the employer

• Design, build, and deploy customer-facing agentic AI products using AWS-native technologies including Strands Agents, AgentCore, Bedrock, and Lambda
• Architect multi-agent systems with reliable tool use, memory, and orchestration patterns that perform accurately in high-stakes financial contexts
• Partner with product managers and customer success to deeply understand user problems and translate them into elegant, production-grade AI solutions
• Own the full lifecycle of AI features - from prompt engineering and agent design through evaluation, deployment, and monitoring
• Write well-designed, well-tested, and maintainable code; participate in code reviews to maintain quality and distribute AI/ML knowledge across the team
• Instrument and monitor agentic systems in production using observability tooling; iterate rapidly based on real user behavior and feedback
• Collaborate cross-functionally with engineers, data teams, and compliance stakeholders to ensure AI outputs meet accuracy and regulatory standards

• 3+ years of professional software engineering experience, with at least 1 year building and shipping AI/LLM-powered applications in production
• Hands-on experience with AWS AI/ML services - Bedrock, Strands, AgentCore, SageMaker, or equivalent agentic frameworks
• Strong understanding of agentic patterns: tool use, RAG, memory management, multi-agent orchestration, and human-in-the-loop design
• Experience designing and evaluating LLM pipelines including prompt engineering, output validation, and hallucination mitigation
• Familiarity with AI observability, evaluation frameworks, and responsible AI practices
• Ability to work in an agile environment and communicate complex AI concepts clearly to both technical and non-technical audiences
• Bachelor's degree in Computer Science, Machine Learning, relevant technical field, or equivalent practical experience

• Competitive cash compensation (based on experience)
• Equity (RSUs)
• Competitive benefits package
• A modern 401(k) plan that includes access to crypto, financial wellness benefits, low fees and more
• Hybrid working model: 3 days in-office, 2 days WFH/flexible
• Monday team lunches, snacks and drinks
• Discretionary Time Off - enjoy the flexibility to rest, refuel, and recharge
• Paid parental leave to bond with your child
• Fertility Benefit
• Autonomous work and flexibility in how work is performed