Senior Software Engineer, Agentic AI at Autodesk
Portland, OR
$117,000–$209,330from the description
Jul 22, 2026
Portland, OR
Jul 23, 2026
What this job asks for AI summary
A senior engineering role focused on building and running cloud-native Java microservices on AWS for a platform that manages product access for a large user base. The work spans the full delivery lifecycle — from design through production support — and includes developing agentic AI systems, automation pipelines, and spec-driven workflows alongside traditional distributed systems responsibilities. Suits engineers with deep Java and AWS experience who also have hands-on exposure to LLM-based tooling and production on-call ownership.
Senior level · 6+ years · Full-time
“or” means any one of them counts — you don't need all of them.
Posted 2 times — it's one opening, so apply once.
We read this from the posting text with AI. Skim the description below before ruling yourself out.
How this req sits in the market our data
Rare in this occupation — lead with these, and say what you built with them.
Most people in this occupation already list these. Still required — just not what gets you shortlisted.
What the occupation pays Median $138,970 (middle half $107,524–$175,762). This posting is about at that midpoint.
Estimated from BLS employment for this occupation and area, per-skill prevalence across our listing corpus, and published wage benchmarks — as of Jul 28, 2026. It is a model, not a headcount.
Why we read it this way (9)
Location is not specified in the posting; the salary range is stated as applying to U.S.-based roles, so the role is treated as US-based. No specific city or metro is mentioned.
Degree requirement is listed as 'Bachelor's degree or higher … or equivalent practical experience'; because equivalent experience is explicitly accepted, no formal degree is hard-gated.
Kinesis and Kafka appear together as interchangeable event-streaming options in the required qualifications ('Kinesis, Kafka, or equivalent'); they are captured as a single skill with alternatives.
Jenkins and GitHub Actions appear together as interchangeable CI/CD options in the required qualifications; captured as a single skill with alternatives.
The 'Technologies we use' section lists additional tools (Splunk, Kibana, Dynatrace, CloudWatch, OpenSearch, SNS, SQS, GitHub, Gradle/Maven, Entra ID, OAuth, OPA, OpenTelemetry) as stack context rather than gated requirements; these are marked preferred.
Gradle and Maven appear together as interchangeable build tools in both the preferred qualifications and the stack section; captured as a single preferred skill with alternatives.
LLM agents, RAG, and tool-calling workflows are explicitly required in the minimum qualifications; RAG also appears in preferred qualifications with additional depth (proactive/event-driven agents, evaluation frameworks) — the base RAG/LLM agent requirement is marked required, and the deeper preferred qualifications around multi-agent patterns and evaluation frameworks are captured under the preferred LLM/RAG/MCP skills.
MCP (Model Context Protocol) integrations are mentioned in the responsibilities and preferred qualifications but not in the minimum qualifications; marked preferred.
Spec-driven development (SDD) is listed as a required qualification but names no specific tool or platform, so it is omitted from the skills list per extraction rules.
Read the full posting
The employer publishes the full description on their own site — read it there ↗. Or sign in to read it here — it's free, and it also lets you track this application.