Senior Applied AI Engineer

Givzey | Version2.ai is a fully remote, AI-native company that created the Autonomous Fundraising category in 2024, when it researched, developed, and deployed the world’s first Autonomous AI to address the labor shortage and capacity gap in nonprofit fundraising. Fundraising teams have a finite capacity to reach donors with one-to-one communication, on average leaving 97% of donors to their organization receiving only marketing communications. A labor shortage compounds the problem: even when organizations want to hire more fundraisers, they often can't find them. The result is a significant capacity gap, where teams can't reach large pools of high-potential donors, resulting in important organizations with world-changing missions being unable to fully execute on their visions. 

Version2.ai's Virtual Engagement Officers (VEOs) close the labor shortage gap with each VEO independently managing a portfolio of up to 1,000 donors, delivering personalized outreach through text, email, video, and robotically handwritten notes year-round. VEOs don't just make staff more efficient; they manage donor portfolios independently, freeing human fundraisers to focus their time on the highest-value relationships while also closing transformational revenue for these organizations. 

VEOs have already generated over $20M in fundraising revenue to date, including individual gifts as large as $100,000, at an opt-out rate of just 0.07%. Organizations deploying a VEO see 4x annual ROI on average, and the top 20% see 8x or higher. More than 250 VEOs are now deployed across higher education, healthcare, and nonprofit organizations in the U.S. and Canada, including UNICEF USA, Bucknell University, Wake Forest University, and William & Mary.

Adam Martel founded Givzey four years ago and leads the company as CEO. He previously founded, scaled, and sold Gravyty, the first company to develop and sell AI-first solutions to nonprofit organizations. 

We're hiring a Senior Applied AI Engineer to lead the technical design and delivery of high-impact AI initiatives across our products.

This is a senior individual contributor and technical leadership role for an experienced software engineer with deep expertise in building production AI systems. You'll lead small teams of engineers responsible for delivering sophisticated AI capabilities, from agentic workflows and retrieval systems to autonomous business processes and intelligent product experiences.

We're looking for someone who brings more than technical expertise. You should be capable of taking ownership of complex initiatives, breaking ambiguous problems into actionable engineering work, making sound architectural decisions, and guiding a team from concept through production delivery.

Equally important, you'll play a significant role in raising the technical maturity of our engineering organization. Through mentorship, code reviews, architectural guidance, and hands-on collaboration, you'll help establish higher standards for software quality, testing, reliability, and maintainability.

We value engineers who combine deep technical ability with practical judgment, strong ownership, and a genuine investment in making the people around them better.

• Agentic AI systems that autonomously execute complex, multi-step business workflows.
• AI-powered product experiences combining LLMs, retrieval, backend services, and human oversight.
• Retrieval and knowledge systems that connect AI agents to organization-specific information.
• Backend services, APIs, and tool integrations enabling AI systems to safely interact with production applications.
• Evaluation, observability, and testing frameworks that improve the quality, consistency, and reliability of AI behavior.
• Orchestration systems and infrastructure supporting scalable, production-grade AI applications.
• Engineering tooling and practices that improve development velocity, software quality, and operational reliability.

• Lead small teams of engineers in the design, development, and delivery of complex, high-impact AI initiatives.
• Own the technical execution of projects from initial design through implementation, testing, deployment, and ongoing operation.
• Translate ambiguous product requirements into clear technical approaches, actionable engineering tasks, and achievable delivery milestones.
• Drive architectural discussions, evaluate technical tradeoffs, and establish sound implementation strategies.
• Coordinate engineering efforts, identify dependencies and blockers, and maintain accountability for technical execution and delivery commitments.
• Remain actively involved in implementation, contributing production code and solving challenging technical problems alongside the team.
• Collaborate closely with Product, Engineering leadership, and stakeholders to ensure technical solutions deliver meaningful business outcomes.

• Design, build, and maintain production-grade AI systems using LLMs, agentic workflows, retrieval architectures, and backend services.
• Develop sophisticated agent workflows involving tool calling, structured outputs, multi-step reasoning, deterministic validation, and human-in-the-loop controls.
• Build and optimize retrieval-augmented generation (RAG) systems, including ingestion pipelines, embeddings, semantic retrieval, and context assembly.
• Integrate foundation models through platforms such as Amazon Bedrock and AWS AgentCore.
• Develop evaluation frameworks for AI workflows, including regression testing, golden datasets, trace analysis, and quality measurement.
• Improve production AI systems for reliability, accuracy, latency, observability, and cost efficiency.
• Design systems that safely handle unpredictable model behavior, edge cases, operational failures, and real-world production constraints.

• Elevate engineering standards through thoughtful code reviews, architectural guidance, hands-on mentorship, and technical leadership.
• Mentor engineers in software design, debugging, testing strategies, system architecture, and production engineering practices.
• Establish and reinforce best practices around code quality, automated testing, documentation, maintainability, and operational readiness.
• Help engineers develop stronger technical judgment, ownership, independence, and problem-solving capabilities.
• Identify recurring technical weaknesses, unnecessary complexity, and process inefficiencies, and actively work to address them.
• Promote a culture of thoughtful engineering where solutions are not simply functional, but reliable, understandable, testable, and maintainable.
• Lead by example through high-quality implementation, effective collaboration, constructive feedback, and strong personal accountability.

• US citizen or authorized to work in the United States.
• 7+ years of professional software engineering experience, with substantial experience designing and delivering production systems.
• Strong proficiency in Python and modern backend software engineering.
• Demonstrated experience providing technical leadership for engineering projects or small teams, including architecture, implementation, mentorship, and delivery.
• Proven hands-on experience designing, building, and shipping production AI applications using LLMs, agentic workflows, retrieval systems, or related technologies.
• Strong knowledge of backend architecture, APIs, distributed systems, databases, and workflow orchestration.
• Experience designing agentic workflows, tool-calling systems, structured outputs, or retrieval-augmented generation architectures.
• Strong understanding of production AI challenges, including model reliability, hallucination mitigation, evaluation, observability, latency, and cost management.
• Demonstrated commitment to software engineering best practices, including automated testing, code review, CI/CD, system design, and maintainability.
• Experience working with cloud infrastructure, preferably AWS.
• Proven ability to mentor engineers, provide constructive technical feedback, and influence engineering practices.
• Strong technical judgment, debugging skills, and the ability to navigate complex systems and ambiguous requirements.
• Ability to balance hands-on engineering contributions with technical leadership responsibilities.
• Excellent communication and collaboration skills, particularly when working across engineering, product, and business teams.
• Experience operating in fast-moving environments where ownership, adaptability, and execution are essential.

• Experience with Amazon Bedrock, AWS AgentCore, Lambda, Step Functions, S3, DynamoDB, RDS, SQS, or related AWS services.
• Experience with LangGraph, LangChain, DSPy, Semantic Kernel, or similar agent orchestration frameworks.
• Experience building multi-step autonomous agents that interact with tools, APIs, external systems, or business workflows.
• Experience developing AI evaluation frameworks, prompt regression testing, trace analysis, or human-in-the-loop review systems.
• Experience with vector databases and semantic retrieval technologies such as OpenSearch, pgvector, Pinecone, Weaviate, or FAISS.
• Experience with LLM observability and evaluation platforms such as LangSmith, Arize, Helicone, Weights & Biases, or OpenTelemetry.
• Experience leading technical initiatives within startup or rapidly scaling SaaS organizations.
• Experience improving engineering practices, introducing development standards, or helping teams increase their technical maturity.
• Experience balancing technical debt, delivery speed, operational reliability, and long-term architectural decisions.

We're looking for an engineer who naturally takes ownership and leads through technical expertise, sound judgment, and example.

Someone who can look at a complicated technical problem, develop a clear approach, bring other engineers along, and drive the work through completion.

Someone who cares deeply about code quality and engineering craftsmanship, but understands the importance of pragmatism and delivering real value.

Someone who enjoys mentoring engineers, challenging assumptions, providing constructive feedback, and helping teammates become more capable and independent.

Someone who understands that technical leadership means being accountable not only for their own contributions, but also for the quality and success of the work they help lead.

Above all, we're looking for someone who makes both our AI systems and our engineering organization stronger.

• High-impact AI initiatives are delivered successfully through effective technical leadership, clear ownership, and strong collaboration.
• AI systems are reliable, observable, maintainable, and trusted by customers and internal teams.
• Engineers working alongside you demonstrate measurable growth in technical ability, independence, and engineering judgment.
• Code quality, testing practices, architectural consistency, and operational reliability improve across the teams you lead.
• Complex technical initiatives move from ambiguous requirements to production-ready solutions with greater consistency and predictability.
• Engineering decisions balance innovation, delivery speed, maintainability, and long-term business value.
• Your technical leadership enables the broader organization to deliver increasingly sophisticated AI capabilities with confidence.