Senior AI Software Engineer, AI Enablement
New
E
ExtendAI software
Remote, USFull-TimeSenior
Salary155,000 - 170,000 USD per year
Apply NowOpens the employer's application page
Job Details
- Experience
- 5+ years shipping production systems
- Required Skills
- AWSPythonOAuthRust
Requirements
- Have 5+ years of experience shipping production systems.
- Be proficient in TypeScript/Node, Python, or Rust.
- Have hands-on experience building with MCP and at least one agent framework or harness: Claude Code, OpenAI Agents SDK, LangChain/LangGraph, CrewAI, AutoGen, or Google ADK.
- Have familiarity with A2A or other agent interoperability protocols.
- Have experience designing and running evaluations for LLM or agent systems and using results to inform shipping decisions.
- Be able to build third-party integrations, including OAuth flows, credential scoping, webhooks, pagination, rate limiting, and retries.
- Have built developer tooling, platforms, or internal tools used by others, with adoption as a measure of success.
- Be able to work directly with non-technical stakeholders, lead working sessions, challenge assumptions constructively, and explain trade-offs plainly.
- Be comfortable with AWS, including Lambda, API Gateway, DynamoDB, and S3.
- Have solid security fundamentals, including IAM, KMS, and serverless attack patterns.
- Be familiar with AI governance and legal or privacy review processes for data access, permissions, tool use, and autonomous actions.
- Use AI tooling regularly and have informed opinions about what works.
Responsibilities
- Pair with business users to analyze workflows, map processes, identify high-leverage problems, and turn requests into technical plans.
- Design and ship secure MCP connectors to internal systems and third-party SaaS.
- Build agent-to-agent integrations using A2A and similar protocols.
- Choose and configure agent harnesses or orchestrators and build multi-agent patterns where useful.
- Establish evaluations for agents and skills using golden datasets, regression suites, LLM-as-judge, tracing, and drift detection.
- Build and curate a shared library of reusable agent skills and connectors.
- Design credential scoping and vending for agent connectors, using OAuth/OIDC where appropriate and least-privilege access.
- Develop risk tiers and review processes for shared skills, including sandboxing and dependency scanning.
- Instrument the platform with OpenTelemetry and make activity visible in Coralogix.
- Write self-serve guides, onboard teams, run user feedback loops, and mentor junior engineers.
View Full Description & ApplyYou'll be redirected to the employer's site