Senior Fullstack AI Platform Engineer

About Kindsight:

Kindsight builds technology that helps fundraisers make a difference. For decades, Kindsight has supported the education, healthcare, and nonprofit sectors with fundraising tools and the largest charitable giving database on the market. And as the giving sector evolves, so does Kindsight. As the leader in fundraising intelligence, Kindsight leverages real-time data and AI to help thousands of organizations around the world identify, manage, and engage with donors - at any scale. With purpose-built CRMs that corral all of that donor information and campaign tracking into one place, donor prospect research tools that offer proactive insights and real-time donor intel, and generative AI that creates personalized, meaningful content drafts at scale, Kindsight’s product suite is truly changing the game for donor fundraising.

Position Summary:

We’re looking for a Senior Fullstack AI Platform Engineer who wants to build AI systems that actually make it into production.

You won’t be spending your time experimenting with prompts or building another chatbot demo. You’ll be building real AI agents and agent-powered workflows on AWS that connect to our products, data, APIs, and internal systems—and are expected to work reliably once customers and teams depend on them.

This is a hands-on engineering role that sits at the intersection of AI application engineering, full-stack development, and platform engineering.

You’ll work across Python backend services, React/TypeScript, Amazon Bedrock, agent runtimes, tool calling, structured outputs, retrieval, evaluation, observability, and system integrations.

Some days you may be building a new agent-backed product experience. Other days, you may be figuring out why an agent made the wrong tool call, improving how we evaluate responses, or creating reusable infrastructure so the next AI feature is faster and safer to ship.

A big part of the job is thinking beyond the first implementation. We want to build patterns that make our AI systems easier to develop, test, deploy, monitor, debug, and maintain as the number of agents and use cases grows.

We’re looking for someone who has already moved beyond prototypes and can talk clearly about what they personally built, the engineering decisions they made, what broke in production, and how they fixed it.

This probably isn’t the right role if your experience is primarily AI research, data science, prompt engineering, or building proof-of-concept chatbots.

It is the right kind of role for an engineer who likes building software, solving messy systems problems, working across the stack, and turning rapidly evolving AI technology into dependable products people can actually use.

What You’ll Do:

• Oversee the building and optimization of production AI agents and agent-backed workflows using Python, AWS, and modern agent frameworks.
• Implement agent logic for planning, tool selection, tool execution, structured responses, multi-step workflows, and error handling.
• Preference for candidates who have built AI, LLM, RAG, or agent-backed workflows used by real users, internal teams, customers, or production-like environments.
• Build integrations between agents and internal APIs, databases, enterprise systems, retrieval sources, and external tools.
• Implement structured output patterns using JSON Schema, Pydantic, validation, retries, and response normalization.
• Work with Amazon Bedrock or comparable managed LLM services for model invocation, inference configuration, prompt handling, and response processing.
• Support AgentCore-style runtime patterns, including session handling, runtime invocation, memory-aware workflows, execution metadata, and agent observability.
• Build RAG workflows using embeddings, vector search, document chunks, metadata filters, retrieval tuning, and source attribution.
• Contribute to MCP-style tool/server integrations and multi-agent handoff patterns where applicable.
• Build Python backend services for agent execution, API integration, job processing, session state, response persistence, and debugging.
• Build React/TypeScript screens for testing agents, reviewing outputs, managing configuration, viewing evaluations, and monitoring execution status.
• Write automated tests for agent behavior, tool calls, structured outputs, retrieval workflows, backend APIs, and frontend flows.
• Support evaluation workflows using test datasets, expected outputs, regression checks, model-based scoring, and human review.
• Troubleshoot real production issues involving tool failures, malformed outputs, retrieval quality, hallucinations, latency, cost, observability gaps, and integration errors.
• Work with senior engineers to implement features within established AWS, CI/CD, security, and observability patterns.

What We’re Looking For:

• 5 years of experience as a fullstack, backend, AI application, platform-adjacent, or infrastructure-minded software engineer.
• 3 years of Python backend engineering experience.
• Hands-on experience building or integrating AI, LLM, RAG, or agent-backed applications.
• Ability to walk through at least one real AI/LLM/agent project in detail, including architecture, users, tools/integrations, failure modes, and what you personally owned.
• Experience with at least one agentic framework or orchestration approach such as Strands, LangGraph, LangChain, Semantic Kernel, AutoGen, CrewAI, or comparable tools.
• Understanding of agentic application patterns: tool calling, structured outputs, planning, multi-turn workflows, session state, memory, retrieval, and evaluation.
• Experience defining or consuming structured outputs using JSON, JSON Schema, Pydantic, OpenAPI, or similar validation approaches.
• Experience integrating applications with REST APIs, internal services, external tools, databases, or enterprise systems.
• Practical exposure to RAG, embeddings, vector databases, semantic search, document chunking, metadata filtering, or retrieval quality tuning.
• Experience with Amazon Bedrock, OpenAI, Anthropic, Azure OpenAI, Vertex AI, or comparable managed LLM services.
• Experience with React and TypeScript, especially building internal tools, forms, tables, validation, loading states, error handling, and API-integrated screens.
• Working familiarity with AWS services such as Lambda, API Gateway, SQS, DynamoDB, S3, CloudWatch, IAM, Step Functions, or Cognito.
• Basic familiarity with infrastructure-as-code, CI/CD, automated testing, and environment-based deployments.
• Strong debugging skills and the ability to explain how you would investigate a failed agent request from API call to model invocation to tool execution to final response.
• Strong communication skills and the ability to explain tradeoffs clearly without relying on buzzwords.

Not a Fit If:

• Your AI experience is limited to prompt writing, tutorials, school projects, or personal chatbot demos.
• You have used AI tools as a developer but have not built software around AI systems.
• You cannot clearly explain what you personally built.
• You are primarily a data scientist, ML researcher, prompt engineer, or frontend-only engineer.
• You are looking for a pure cloud infrastructure role with little hands-on AI application work.

You are looking for a pure application feature role with no interest in platform patterns, testing, observability, or reliability.

Strong Signals:

• You have built several production ready AI agent or LLM-backed workflow used by actual users at scale.
• You have debugged production or near-production AI failures such as bad tool selection, hallucinated answers, malformed JSON, poor retrieval, latency spikes, or failed integrations.
• You understand the difference between a chatbot, an LLM-backed backend workflow, and a true agent.
• You can explain how structured outputs, tool schemas, validation, retries, and observability make AI systems reliable.
• You have worked in a platform, infrastructure, DevOps, backend, or internal tools environment and enjoy building reusable patterns.

Compensation Range: $140,000-$165,000 OTE (base and bonus) annually, based on experience, market benchmarks and role complexity. We aim to offer fair, competitive pay that reflects your skills and the market.

This advertised position is for an existing vacancy at Kindsight. At Kindsight, we’re proud to be a place where everyone belongs and has an equal opportunity to contribute, thrive and grow. We hire based on skills, potential, and impact, and we believe our differences fuel innovation. We welcome all individuals and do not discriminate on the basis of gender identity and expression, race, ethnicity, disability, sexual orientation, colour, religion, creed, gender, national origin, age, marital status, pregnancy, sex, citizenship, education, languages spoken or veteran status. We’re building a workplace where everyone has the opportunity to do meaningful work and make a difference.

We leverage artificial intelligence (AI) tools to support certain aspects of our recruitment process. These tools may help with resume screening, drafting job descriptions, creating interview questions and occasionally identifying potential candidates. All hiring decisions are made by our people, not AI. Our intent is to use AI thoughtfully to streamline administrative tasks, improve the candidate experience and support fair, unbiased hiring practices consistent with industry standards.