Senior Software Engineer – AI

This is a fully remote position, open to applicants in Canada, +1 more country.

📋 Description

• Develop production AI solutions within Network Solutions, encompassing conversational agents, business and website generation, knowledge and FAQ agents, content experiences, domain discovery, and intelligent automation.

• Convert ambiguously defined product challenges into actionable AI solutions.

• Assess various methodologies and independently transform the most effective solution into dependable, secure, observable, and cost-effective production systems.

• Design and create production AI services utilizing Python, FastAPI, asynchronous workers, PostgreSQL, Redis, queues, model APIs, and external tools.

• Construct dependable tool-calling agents and multi-step workflows that interact with internal APIs, MCP tools, business systems, and knowledge bases.

• Design event-driven systems that incorporate retries, dead-letter handling, idempotency, back pressure, and recovery from failures.

• Develop and enhance RAG systems that include ingestion, chunking, embeddings, hybrid retrieval, reranking, metadata filtering, context construction, and citations.

• Experiment with models from OpenAI, Anthropic, Google, xAI, and open-weight ecosystems.

• Establish AI evaluation pipelines utilizing curated datasets, regression tests, retrieval metrics, LLM-as-judge techniques, groundedness checks, and tool-execution evaluations.

• Identify hallucinations, retrieval failures, incorrect tool utilization, agent loops, latency issues, provider failures, and unexpected inference costs.

• Leverage AI coding agents to expedite design, implementation, testing, debugging, and refactoring.

• Translate product objectives into testable technical hypotheses and quickly prototype alternatives.

• Set quality, latency, reliability, safety, and cost benchmarks and assess production performance.

• Take ownership of implementation across APIs, workflows, data, queues, model integration, evaluations, observability, and production support.

⛳️ Requirements

• Minimum of 5 years of professional experience in software engineering focused on building production backend, distributed, or cloud-based systems.

• Practical experience in creating Applied AI, LLM, RAG, NLP, or agent-based applications with substantial production exposure.

• Proficient in Python, including advanced skills in FastAPI, asynchronous programming, Pydantic, SQLAlchemy or SQLModel, and production API development.

• Solid understanding of backend and distributed systems, including REST APIs, concurrency, background processing, caching, reliability, and production debugging.

• Production experience with RabbitMQ, Kafka, Azure Service Bus, or similar queue and messaging infrastructures.

• Hands-on experience with LLM APIs, developing structured output, function calling, tool calling, or agent execution workflows.

• Experience in building at least one RAG or knowledge-grounded system with quantifiable quality and latency results.

• Strong PostgreSQL and data modeling expertise, along with experience in utilizing Redis, pgvector, vector databases, or hybrid search technologies.

• Proven experience using AI coding agents such as Cursor, Claude Code, Codex, or comparable tools as an integral part of daily software engineering tasks.

• Comfortable with understanding the behavior, failures, and scalability of modern AI systems in production.

• Deep knowledge of prompting, structured outputs, tool schemas, context management, model routing, retries, fallbacks, rate limits, and streaming responses.

• Ability to design experiments and evaluations based on measurable outcomes.

• Familiarity with retrieval quality, grounding, hallucination mitigation, prompt injection risks, tool authorization, and practical agent guardrails.

• Experience with Docker, CI/CD, automated testing, observability, distributed tracing, OpenTelemetry, Langfuse, or similar tools.

• Experience with Semantic Kernel, Microsoft Agent Framework, LangGraph, PydanticAI, or equivalent agent frameworks.

• Experience in building or utilizing Model Context Protocol tools and servers, or working with model gateways like LiteLLM.

• Familiarity with Azure AI Search, pgvector, Chroma, Kubernetes, Azure, OCI, or comparable production AI platform technologies.

• Experience in developing high-scale customer-facing AI products, open-weight model inference, AI safety controls, or automated agent evaluation systems.

🏝️ Benefits

• Comprehensive health insurance coverage.

• Flexible work hours and the option for remote work.

• Opportunities for professional development and training.

• Collaborative and innovative work environment.

• Competitive salary with performance-based incentives.