Software Engineer - AI

We are looking for a hands on Applied AI Engineer who combines strong software engineering fundamentals with practical AI problem solving. You will help build production AI experiences across Network Solutions, including conversational agents, business and website creation, knowledge and FAQ agents, content experiences, domain discovery, and intelligent automation. 

You will work with senior engineers, architects, and product partners to turn customer and product problems into reliable, secure, observable, and cost efficient AI systems. This is an applied engineering role focused on building, measuring, and continuously improving real AI products.

Who you are & what you’ll need to succeed

• Translate product requirements into practical AI solutions using LLMs, RAG, tool calling, agents, deterministic workflows, or traditional software where appropriate. 

• Build production AI services using Python, FastAPI, asynchronous workers, PostgreSQL, Redis, queues, model APIs, and external tools. 

• Implement reliable tool calling agents and multi step workflows that interact with internal APIs, MCP tools, business systems, and knowledge sources. 

• Build event driven workflows using RabbitMQ, Kafka, Azure Service Bus, or equivalent platforms, including retries, dead letter handling, idempotency, and failure recovery. 

• Build and improve RAG systems covering ingestion, chunking, embeddings, hybrid retrieval, reranking, metadata filtering, context construction, and citations. 

• Integrate models from OpenAI, Anthropic, Google, xAI, and open weight ecosystems, and help select models based on quality, latency, reliability, and cost. 

• Build and run AI evaluations using curated datasets, regression tests, retrieval metrics, LLM as judge techniques, groundedness checks, and tool execution evaluation. 

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

• Operate as an AI powered engineer using Cursor, Claude Code, OpenAI Codex, or equivalent coding agents to accelerate implementation, testing, debugging, refactoring, and documentation.

What we’re looking for 

You should be comfortable going beyond a working demo and understand the core engineering patterns needed to make AI systems reliable in production. 

• Understanding of prompting, structured outputs, tool schemas, context management, retries, fallbacks, rate limits, caching, and streaming responses. 

• Ability to use experiments and evaluations to compare approaches using measurable outcomes rather than subjective testing alone. 

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

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

You will often receive a product goal or technical direction rather than a fully specified implementation. You should be able to break the problem into manageable pieces, validate assumptions, implement the solution, and work with senior engineers when architecture tradeoffs require discussion. 

• Turn product goals into testable technical tasks and prototype alternatives when the best approach is not obvious. 

• Choose simple, maintainable solutions and avoid using an agent or LLM when a deterministic approach solves the problem better. 

• Measure quality, latency, reliability, safety, and cost and use those signals to improve the solution over time. 

• Own implementation across APIs, workflows, data, queues, model integration, evaluations, observability, and production support for assigned features. 

• Use AI coding agents aggressively to increase engineering velocity while preserving testing discipline, security, maintainability, and code quality.