
Software Engineer – AI
Posted Sep 15

Posted Sep 15
This is a fully remote position, open to applicants in Canada, +1 more country.
• Develop production AI experiences within Network Solutions, encompassing conversational agents, business and website development, knowledge and FAQ agents, content experiences, domain discovery, and intelligent automation.
• Convert product requirements into actionable AI solutions utilizing LLMs, RAG, tool invocation, agents, deterministic workflows, or traditional software when suitable.
• Create production AI services employing Python, FastAPI, asynchronous workers, PostgreSQL, Redis, queues, model APIs, and external tools.
• Establish dependable tool-calling agents and multi-step workflows that engage with internal APIs, MCP tools, business systems, and knowledge resources.
• Design event-driven workflows incorporating retries, dead-letter handling, idempotency, and failure recovery.
• Develop and enhance RAG systems that address ingestion, chunking, embeddings, hybrid retrieval, reranking, metadata filtering, context construction, and citations.
• Integrate models from OpenAI, Anthropic, Google, xAI, and open-weight ecosystems.
• Conduct AI evaluations using curated datasets, regression tests, retrieval metrics, LLM-as-judge methodologies, groundedness checks, and tool-execution assessments.
• Troubleshoot hallucinations, retrieval failures, incorrect tool usage, agent loops, latency challenges, provider issues, and unexpected inference expenses.
• Decompose product objectives into manageable components, validate assumptions, implement solutions, and engage in architectural discussions with senior engineers.
• Transform product objectives into testable technical tasks and prototype alternative solutions.
• Assess quality, latency, reliability, safety, and costs, utilizing those insights to enhance solutions.
• Oversee implementation across APIs, workflows, data, queues, model integration, evaluations, observability, and production support for assigned features.
• Leverage AI coding agents to boost engineering efficiency while upholding testing discipline, security, maintainability, and code quality.
• Minimum of 3 years of professional software engineering experience in building production backend, distributed, or cloud-based systems.
• At least 1 year of practical experience in developing Applied AI, LLM, RAG, NLP, or agent-based applications.
• Proficient in Python, including FastAPI, asynchronous programming, Pydantic, SQLAlchemy or SQLModel, and production API development.
• Strong understanding of backend and distributed systems principles, including REST APIs, concurrency, background processing, caching, reliability, and production debugging.
• Practical experience with RabbitMQ, Kafka, Azure Service Bus, or similar queue and messaging architectures is essential.
• Experience in integrating LLM APIs and creating structured outputs, function calling, tool invocation, or agent execution workflows.
• Background in building or contributing to a RAG or knowledge-grounded system, covering retrieval, embeddings, indexing, context construction, and evaluation.
• Familiarity with PostgreSQL and data modeling, with exposure to Redis, pgvector, vector databases, or hybrid search technologies.
• Proven experience using AI coding agents such as Cursor, Claude Code, Codex, or similar tools as an integral part of software engineering tasks.
• Competitive salary and performance-based bonuses.
• Flexible working hours and remote work options.
• Comprehensive health, dental, and vision insurance.
• Opportunities for professional development and continuous learning.
• Collaborative and innovative work environment.
Alzheimer's Association®
Capital One
Capital One
Get handpicked remote jobs straight to your inbox weekly.