{"id":1231643,"url":"https://alion.io/job/kindsight-senior-agentic-ai-platform-engineer","title":"Senior Agentic AI Platform Engineer","company":{"id":1858233,"name":"Kindsight","domain":"kindsight.io","url":"https://alion.io/company/kindsight","size_band":"201-500","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Schema","truth_index":null},"role":"AI/ML","role_family":"AI/ML","seniority":"senior","employment_type":"full_time","work_mode":"remote","remote_scope":"stated_countries","remote_scope_basis":"board_field","remote_working_hours":null,"hiring_geo_confidence":"structured","locations":[],"countries":[],"hiring_countries":["CA"],"hiring_countries_total":1,"salary":{"min":140000,"max":165000,"currency":"CAD","period":"year","gross":null,"usd_annual":116730},"salary_estimate":null,"experience_years_min":5,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AI Agents","optional":false},{"name":"Amazon CloudWatch","optional":false},{"name":"Amazon S3","optional":false},{"name":"Anthropic","optional":false},{"name":"API Gateway","optional":false},{"name":"AutoGen","optional":false},{"name":"AWS","optional":false},{"name":"AWS Bedrock","optional":false},{"name":"AWS Bedrock AgentCore","optional":false},{"name":"AWS Lambda","optional":false},{"name":"AWS Step Functions","optional":false},{"name":"AWS Strands Agents","optional":false},{"name":"Azure","optional":false},{"name":"CI/CD","optional":false},{"name":"CrewAI","optional":false},{"name":"DynamoDB","optional":false},{"name":"Embeddings","optional":false},{"name":"Function Calling","optional":false},{"name":"IAM","optional":false},{"name":"LangChain","optional":false},{"name":"LangGraph","optional":false},{"name":"LLM","optional":false},{"name":"Model Context Protocol","optional":false},{"name":"OpenAI","optional":false},{"name":"Platform Engineering","optional":false},{"name":"Prompt Engineering","optional":false},{"name":"Pydantic","optional":false},{"name":"Python","optional":false},{"name":"RAG","optional":false},{"name":"React.js","optional":false},{"name":"Rest API","optional":false},{"name":"Semantic Kernel","optional":false},{"name":"Semantic Search","optional":false},{"name":"Semantic Search","optional":false},{"name":"Structured Outputs","optional":false},{"name":"Tool Use","optional":false},{"name":"TypeScript","optional":false},{"name":"Vertex AI","optional":false},{"name":"JavaScript","optional":true}],"status":"live","first_seen_at":"2026-06-24T21:37:59Z","employer_posted_date":"2026-09-25","last_verified_at":"2026-09-27T03:58:26Z","board_verified":true,"closed_at":null,"days_open":94,"trust":{"level":"stale","repost_count":0,"flags":["stale"],"days_open":93},"description":"About Kindsight:\nKindsight 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.\nPosition Summary:\nWe’re looking for a Senior Agentic AI Platform Engineer who wants to build AI systems that actually make it into production.\nYou won’t be spending your time experimenting with prompts or building another chatbot demo.\nYou’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.\nThis is a hands-on engineering role that sits at the intersection of AI application engineering, full-stack development, and platform engineering.\nYou’ll work across Python backend services, React/TypeScript, Amazon Bedrock, agent runtimes, tool calling, structured outputs, retrieval, evaluation, observability, and system integrations.\nSome 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.\nA 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.\nWe’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.\nThis probably isn’t the right role if your experience is primarily AI research, data science, prompt engineering, or building proof-of-concept chatbots.\nIt 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.\nWhat You’ll Do:\nOversee the building and optimization of production AI agents and agent-backed workflows using Python, AWS, and modern agent frameworks.\n\nImplement agent logic for planning, tool selection, tool execution, structured responses, multi-step workflows, and error handling.\n\nPreference for candidates who have built AI, LLM, RAG, or agent-backed workflows used by real users, internal teams, customers, or production-like environments.\n\nBuild integrations between agents and internal APIs, databases, enterprise systems, retrieval sources, and external tools.\n\nImplement structured output patterns using JSON Schema, Pydantic, validation, retries, and response normalization.\n\nWork with Amazon Bedrock or comparable managed LLM services for model invocation, inference configuration, prompt handling, and response processing.\n\nSupport AgentCore-style runtime patterns, including session handling, runtime invocation, memory-aware workflows, execution metadata, and agent observability.\n\nBuild RAG workflows using embeddings, vector search, document chunks, metadata filters, retrieval tuning, and source attribution.\n\nContribute to MCP-style tool/server integrations and multi-agent handoff patterns where applicable.\n\nBuild Python backend services for agent execution, API integration, job processing, session state, response persistence, and debugging.\n\nBuild React/TypeScript screens for testing agents, reviewing outputs, managing configuration, viewing evaluations, and monitoring execution status.\n\nWrite automated tests for agent behavior, tool calls, structured outputs, retrieval workflows, backend APIs, and frontend flows.\n\nSupport evaluation workflows using test datasets, expected outputs, regression checks, model-based scoring, and human review.\n\nTroubleshoot real production issues involving tool failures, malformed outputs, retrieval quality, hallucinations, latency, cost, observability gaps, and integration errors.\n\nWork with senior engineers to implement features within established AWS, CI/CD, security, and observability patterns.\n\nWhat We’re Looking For:\n5 years of experience as a fullstack, backend, AI application, platform-adjacent, or infrastructure-minded software engineer.\n\n3 years of Python backend engineering experience.\n\nHands-on experience building or integrating AI, LLM, RAG, or agent-backed applications.\n\nAbility 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.\n\nExperience with at least one agentic framework or orchestration approach such as Strands, LangGraph, LangChain, Semantic Kernel, AutoGen, CrewAI, or comparable tools.\n\nUnderstanding of agentic application patterns: tool calling, structured outputs, planning, multi-turn workflows, session state, memory, retrieval, and evaluation.\n\nExperience defining or consuming structured outputs using JSON, JSON Schema, Pydantic, OpenAPI, or similar validation approaches.\n\nExperience integrating applications with REST APIs, internal services, external tools, databases, or enterprise systems.\n\nPractical exposure to RAG, embeddings, vector databases, semantic search, document chunking, metadata filtering, or retrieval quality tuning.\n\nExperience with Amazon Bedrock, OpenAI, Anthropic, Azure OpenAI, Vertex AI, or comparable managed LLM services.\n\nExperience with React and TypeScript, especially building internal tools, forms, tables, validation, loading states, error handling, and API-integrated screens.\n\nWorking familiarity with AWS services such as Lambda, API Gateway, SQS, DynamoDB, S3, CloudWatch, IAM, Step Functions, or Cognito.\n\nBasic familiarity with infrastructure-as-code, CI/CD, automated testing, and environment-based deployments.\n\nStrong 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.\n\nStrong communication skills and the ability to explain tradeoffs clearly without relying on buzzwords.\n\nNot a Fit If:\nYour AI experience is limited to prompt writing, tutorials, school projects, or personal chatbot demos.\n\nYou have used AI tools as a developer but have not built software around AI systems.\n\nYou cannot clearly explain what you personally built.\n\nYou are primarily a data scientist, ML researcher, prompt engineer, or frontend-only engineer.\n\nYou are looking for a pure cloud infrastructure role with little hands-on AI application work.\n\nYou are looking for a pure application feature role with no interest in platform patterns, testing, observability, or reliability.\nStrong Signals:\nYou have built several production ready AI agent or LLM-backed workflow used by actual users at scale.\n\nYou have debugged production or near-production AI failures such as bad tool selection, hallucinated answers, malformed JSON, poor retrieval, latency spikes, or failed integrations.\n\nYou understand the difference between a chatbot, an LLM-backed backend workflow, and a true agent.\n\nYou can explain how structured outputs, tool schemas, validation, retries, and observability make AI systems reliable.\n\nYou have worked in a platform, infrastructure, DevOps, backend, or internal tools environment and enjoy building reusable patterns.\n\nCompensation 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.\nThis advertised position is for an existing vacancy at Kindsight.\nAt 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.\nWe 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 .","description_format":"text","description_chars":9388,"description_truncated":false,"requirements":{"experience_years_min":5,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":null,"security_clearance":false,"languages":[]},"benefits":[],"hiring_locations":[{"name":"Canada","iso":"CA","kind":"country"}],"hiring_excludes":[],"relocation_offered":false,"industries":["Professional Services","Nonprofits & Foundations"],"lifecycle":[{"event":"open","at":"2026-09-25T15:02:43Z"}],"liveness":{"score":13,"band":"cold","label":"Long shot","p_open":1,"p_active":0.449,"p_room":0.28,"age_days":93,"expected_fill_days":41,"reasons":["conf:3","win:tail","crowd:"],"computed_at":"2026-09-26T05:45:00Z"},"pay":{"stated_usd_annual":116730,"is_top_pay":false},"html_url":"https://alion.io/job/kindsight-senior-agentic-ai-platform-engineer","json_url":"https://alion.io/job/kindsight-senior-agentic-ai-platform-engineer.json","meta":{"generated_at":"2026-09-27T04:49:54Z","cache_seconds":300,"methodology":"https://alion.io/methodology","terms":"https://alion.io/terms","contact":"https://alion.io/contact","api":"https://alion.io/developers","usage":{"tier":"crawler","counted_by":"address","units_charged":1,"used_today":4200,"day_limit":5000,"remaining_today":800,"minute_limit":60,"resets_at":"2026-09-28T00:00:00Z"}}}