Staff AI Agent Engineer
Posted yesterday
The role in short
Design, build, and deploy production AI agents and integrations for insurance customers, owning complex launches and turning bespoke solutions into reusable engineering patterns.
About Us:
Liberate builds AI agents to automate manual tasks for the $2.7T insurance industry. We started with voice — the hardest and most valuable channel in insurance — and are now expanding into full workflow automation across sales, servicing, and claims. Our long-term vision is to build reasoning agents capable of handling the entire spectrum of insurance carrier and broker operations. We've raised $72M to date, including a $50M Series B in October 2025, backed by top-tier venture firms.
Location: Boston or San Francisco (Berkeley), hybrid (2 days/week in office)
About the Role
As a Staff AI Agent Engineer, you are a force multiplier for customer deployments and agent quality. You own complex customer launches end to end and turn hard, bespoke problems into repeatable patterns. You operate with strong judgment, raise the engineering bar in the work, and reduce dependency on leadership by owning outcomes directly.
This role is hands-on, customer-facing, and deeply technical. You are not a solutions engineer. You are an engineer who ships.
What You’ll Do
- Own complex, high-impact agent deployments from design through production
- Design, build, and iterate on agent workflows, prompts, evals, and integrations
- Turn customer-specific learnings into reusable templates, playbooks, and patterns
- Partner with Product and Platform to influence roadmap based on real-world usage
- Debug and improve agent behavior using structured evals, monitoring, and analysis
- Lead technical reviews for agent design, launch readiness, and post-launch quality
- Mentor other Agent Engineers through example and direct coaching
- Raise the bar on engineering quality, operational rigor, and reuse in deployments
What We’re Looking For
Must Have
- 6+ years of professional software engineering experience
- Strong hands-on experience building and operating production systems
- Fluency in Python and modern backend systems (APIs, services, cloud)
- Experience working with LLM-based systems, prompts, tools, or agent frameworks
- Ability to reason about quality, failure modes, and operational risk
- Comfort working directly with customers on technically complex problems
- High ownership, good judgment, and the ability to operate under pressure
Nice to Have
- Experience with agentic systems, eval frameworks, or AI observability
- Prior work in B2B SaaS, enterprise software, or regulated environments
- Experience turning bespoke solutions into reusable systems
Prep for this interview
4 questions likely to come up at Liberate, each matched to a line in this posting.
- 1LLMs, RAG and agents
They wrote: “Experience working with LLM-based systems, prompts, tools, or agent frameworks”
When would you use an agent that takes actions, and how do you keep it safe?
How to answer
Why they ask: Agent work is growing fast in FDE postings. Senior candidates are expected to know where agents fail.
- Use agents for multi-step tasks with clear success checks; avoid them where one wrong action is costly
- Give the agent narrow tools and permissions, not broad access
- Require human approval for risky actions
- Log every step so the customer can audit it
Tip: Start from the cost of a wrong action. Limit what the agent can do, and log everything.
- 2Integrations and APIs
They wrote: “Design, build, and iterate on agent workflows, prompts, evals, and integrations”
Walk me through connecting our product to a customer's internal system that has no documentation.
How to answer
Why they ask: This happens weekly in the job. They want a calm, step-by-step method.
- Find who owns the system and get read access to a test environment
- Watch real traffic or logs to learn the data shapes
- Build a thin adapter with logging around every call
- Agree on how failures get reported, and who fixes what
Tip: Talk about finding the owner of the system first. The code is the easy part.
- 3Coding
They wrote: “6+ years of professional software engineering experience”
Build a small in-memory cache. Then add expiry. Then a size limit.
How to answer
Why they ask: Staged exercises show how your code holds up when requirements change mid-interview, like at a customer.
- Start with get and set on a dictionary, plus tests
- Store an expiry time with each value and check it on read
- Track use order and evict the least recently used entry when full
- Say what you'd change for many threads or many machines
Tip: Keep the first version simple and well tested so the next stage is a small change.
- 4Ownership and working with customers
They wrote: “High ownership, good judgment, and the ability to operate under pressure”
Tell me about something you shipped that broke in production.
How to answer
Why they ask: Everyone has broken production. They want to hear you own it and change something afterwards.
- What broke and who it affected
- How you found out and what you did in the first hour
- The root cause, said plainly
- What you changed so it can't happen the same way again
Tip: Pick a real one with a cost. Spend most of the answer on what you changed.
Not the one? Get the next one by email
New roles land here every day. Pick what you want to hear about.
Want the job, not just the posting? Learn how FDEs work.
FDE Info is our free weekly newsletter for forward deployed engineers: tools, field notes from real deployments, and how FDE teams hire and pay.
Free. One email a week. Unsubscribe in one click.

