Skip to content

Open nowPosted 9 hours ago

Senior AI Software Engineer, AI Enablement

Extend13 open roles

Where
Remote, US
Work mode
Remote
Get the CV for this job

From $25 per CV, paid once. No subscription.

Your applicationOpen nowSenior AI Software Engineer, AI EnablementExtend · Remote, US
  1. YouYes, apply to this one.

  2. CV RocketCV written for this posting.

  3. 25 readersRecruiter, hiring manager, skeptic. Round after round.

  4. CV RocketApplied on Extend's own form.

The reply lands in your private mailbox

3×more interviews than doing it yourself with ChatGPT.

The clock on this job

Early applications get read.

14.3% of postings close within 7 days. Measured by our own scanner across the market. Extend postings stay open a median of 39 days.

Share of postings closed within
  1. 2.2%1 day
  2. 4.7%3 days
  3. 14.3%7 days
  4. 23.0%14 days
  5. 39.3%30 days
  6. 59.3%60 days
This job: posted 9 hours ago

Extend median: 39 days open

The posting

About Extend:

Extend is revolutionizing the post-purchase experience for retailers and their customers by providing merchants with AI-driven solutions that enhance customer satisfaction and drive revenue growth. Our comprehensive platform offers automated customer service handling, seamless returns/exchange management, end-to-end automated fulfillment, and product protection and shipping protection alongside Extend's best-in-class fraud detection. By integrating leading-edge technology with exceptional customer service, Extend empowers businesses to build trust and loyalty among consumers while reducing costs and increasing profits.

Today, Extend works with more than 1,000 leading merchant partners across industries, including fashion/apparel, cosmetics, furniture, jewelry, consumer electronics, auto parts, sports and fitness, and much more. Extend is backed by some of the most prominent technology investors in the industry, and our headquarters is in downtown San Francisco.

About the Role

The AI Enablement team gives every team at Extend the AI tooling it needs to do its best work. We pair directly with business users in finance, support, claims, sales, recruiting, and operations to understand how they work, then build the agents, connectors, and skills that change it. This is an engineering role first. Sitting beside a business user is how you find the right problem. Solving it takes real engineering judgment about agent harnesses, protocols, security, and reliability.

You will build on the platform that turns one-off prototypes into durable, secure, measurable tooling: MCP connectors to the systems we run on, agent-to-agent (A2A) integrations, a shared library of agent skills, and the evaluation practice that tells us whether any of it actually works.

What You'll Do

  • Pair with business users to run workflow analysis and process mapping, find the highest-leverage problems, and turn ambiguous requests into scoped technical plans.
  • Design and ship secure MCP connectors to Extend's internal systems and third-party SaaS: finance, CRM, data warehouse, expense management, product analytics, support, ATS, and the long tail beyond.
  • Build agent-to-agent integrations using A2A and similar protocols, so specialized agents can delegate to each other safely across domains.
  • Choose and configure the right agent harness or orchestrator for each job, and build multi-agent patterns (planner/executor, specialized sub-agents) where they genuinely help.
  • Stand up Extend's evaluation practice for agents and skills: golden datasets, regression suites, LLM-as-judge, tracing, and drift detection. Every shipped skill should have a way to prove it works and to notice when it stops working.
  • Build and curate the shared library of agent skills every team composes from. Codify patterns and raise the floor for what a safe, high-quality skill looks like. Treat every engagement as a source of reusable skills and connectors.
  • Design credential scoping and vending for agent connectors: per-user, per-skill, per-connector keys, OAuth/OIDC where it fits, least-privilege everywhere.
  • Build the risk-tier and review model for shared skills, including sandboxing and dependency scanning for skills that pull in untrusted packages. Partner with legal, security, and privacy on governance review for agents that touch sensitive data or take autonomous actions.
  • Instrument the platform end to end with OpenTelemetry so every MCP call, skill execution, and credential use is visible in Coralogix.
  • Own adoption. Write self-serve guides, onboard teams, and run the feedback loop between what shipped and what users actually need. The work is done when the team using it is self-sufficient.
  • Mentor more junior engineers on the team in evals, agent design, and secure integration work.

What We're Looking For

  • 5+ years shipping production systems, and you can point to where they held, where they broke, and what you changed.
  • Proficient in TypeScript/Node, Python, or Rust.
  • Hands-on experience building with MCP and at least one agent framework or harness (Claude Code, OpenAI Agents SDK, LangChain/LangGraph, CrewAI, AutoGen, Google ADK). Familiarity with A2A or other agent interoperability protocols.
  • Experience designing and running evals for LLM or agent systems, and using the results to make shipping decisions.
  • You can build real third-party integrations: OAuth flows, credential scoping, webhooks, pagination, rate limiting, retries.
  • You've built developer tooling, platforms, or internal tools that other people depended on, and you measure that work by adoption.
  • You can work directly with non-technical stakeholders: run a working session, challenge assumptions constructively, and explain trade-offs in plain language.
  • Comfortable on AWS (Lambda, API Gateway, DynamoDB, S3) with solid security fundamentals: IAM, KMS, serverless attack patterns.
  • Familiarity with AI governance and legal or privacy review processes, including risks around data access, permissions, tool use, and autonomous actions.
  • You use AI tooling every day and have opinions about what works.

Nice to Have

  • Eval and observability tooling: LangSmith, Langfuse, Braintrust, OpenTelemetry, Coralogix, Datadog.
  • LLM application security: OWASP Top 10 for LLMs and agentic applications, prompt injection defense, agent sandboxing.
  • AWS CDK, CloudFormation, or similar infrastructure-as-code.
  • Background in platform engineering, internal developer platforms, or enterprise integration.
  • Prior IC role at an early-stage startup with a small team and a wide surface area.

Expected Pay Range: $155,000 - $170,000 per year salaried*

* The target base salary range for this position is listed above. Individual salaries are determined based on a number of factors including, but not limited to, job-related knowledge, skills and experience.

Extend does not provide immigration-related sponsorship for this role.

Life at Extend:

  • Working with a great team from diverse backgrounds in a collaborative and supportive environment.
  • Competitive salary based on experience, with full medical and dental & vision benefits.
  • Stock in an early-stage startup growing quickly.
  • Generous, flexible paid time off policy.
  • 401(k) with Financial Guidance from Morgan Stanley.

Extend CCPA HR Notice

From $25, paid onceGet the CV for this job

What happens when you press

One press. We do the rest.

  1. A CV for this posting

    Written against Extend's own wording, from every piece of relevant proof in your profile.

  2. 25 readers review it

    Recruiter, hiring manager, skeptic and more read every draft, round after round. You get the best round.

    The review screen in CV Rocket: how each CV was read, round by round.
  3. We apply on Extend's form

    Our application engine gets through the hardest forms there are. Where a question needs you, AI suggests the best answer. Don't want us applying from our IP addresses? Use our Chrome extension: we apply straight from your own browser.

    An application in CV Rocket: every answer filled in on the employer's form.
  4. Every reply, sorted

    Extend's answer lands in your private mailbox, and we classify it on arrival: interview, question, rejection.

    The CV Rocket inbox: each employer reply classified as an interview, an action or a rejection.
  5. Reply with AI

    AI helps you write the email, checks it and sends it. We show you whether the recruiter read it.

  6. The interview in your calendar

    Full integration with your calendar. The invitation goes straight in.

    An interview invitation in the CV Rocket inbox, added to the candidate's calendar.
Get the CV for this job

From $25 per CV, paid once. No subscription.

Why it works

3×

more interviews than doing it yourself with ChatGPT.

ChatGPT writes a CV and never learns what happened to it. We see every reply. For each CV we know:

  • How it was written, and how the review scored it
  • When we applied, and how long after the posting went up
  • Which posting, which company, which city
  • Who got the interview, and who heard nothing

That is how we know which CVs get called.

Get the CV for this job

From $25 per CV, paid once. No subscription.

The numbers game

More applications. More interviews.

Every application goes out with its own CV, written for that posting and paid once. Send enough of them and the law of large numbers finds you the job.

By hand5–10
With CV Rocket100
applications a day

Nearby

Live postings like this one

Same employer first, then the same role elsewhere.

Before you press

Straight answers

Get the CV for this job

From $25 per CV, paid once. No subscription.

What if my background isn't good enough?

We make the most of the background you have. The CV uses every piece of relevant proof your profile holds, and one of the 25 readers reads your whole profile and flags what the CV left out.

Do you really apply for me?

Yes, on the employer's own form, the hardest ones included. Where a question needs you, you answer it right there and AI suggests the best answer. Don't want us applying from our IP addresses? Use our Chrome extension: we apply straight from your own browser.

Is it a subscription?

No. You pay once per CV, from $25. Every application goes out with its own CV, written for that posting.

One job. One CV.
Paid once.

Pick the posting you want. We write for it, apply for you and catch the reply.

Get the CV for this job

From $25 per CV, paid once. No subscription.