Bland AI
Bland AI

Agent Solutions Engineer

$120–200kSan Francisco, CAOn-siteMidFull-time

Posted 10 days ago

The role in short

Embed with customers to design, build, and deploy production-ready AI voice agents and integrations, owning the technical delivery from discovery to adoption.

Agent Solutions Engineer

About Bland AI

We’re a Series C startup, and have raised $100 million from Emergence Capital, Y Combinator, Dell Technologies Capital and the founders of PayPal and Twilio. Bland.ai builds AI voice agents that handle real phone calls for some of the largest companies in the world. Our software runs inside critical workflows at companies like Samsara, Gallup, TripAdvisor, Snapchat, Signant Health, Better.com, and others.

Why This Role Exists

Every customer is different — the problems they’re solving, the data they have, and the impact they want to create with AI. We’re looking for someone who thrives in that ambiguity, who can take fuzzy goals and transform them into working, production-ready agents that deliver real value. You’ll work directly with customers to understand their workflows, build tailored agents, and help shape how Bland is adopted across their organization.

What You’ll Do

  • Design and deploy AI solutions. Work closely with customers to translate their challenges into functional agents, integrating APIs and data sources to automate real business processes.
  • Prototype fast, iterate faster. Build the first version quickly, get it into production, and refine based on real-world feedback.
  • Collaborate deeply. Partner with customer teams across engineering, product, and operations to ensure the agent performs, scales, and delivers measurable outcomes.
  • Own end-to-end delivery. From discovery call to deployment, you’ll lead the technical build, testing, and iteration — ensuring the experience feels natural, human, and on-brand.
  • Drive adoption and expansion. Share results, train teams, and embed yourself within the customer organization to uncover new opportunities for automation and scale.
  • Be the face of Bland. You are the customer’s champion, their best employee, and you treat them with unreasonable hospitality. You travel on-site, get to know our customers on a human level, and develop real relationships with our champions and other stakeholders, going above and beyond to host training sessions and dinners.

Must-Have Qualifications

  • 3–10 years of experience in full-stack, AI, or solutions engineering roles where you owned builds from concept to production.
  • Proven experience building and integrating AI or automation features into real-world applications.
  • Hands-on experience integrating LLMs or AI SDKs into web applications.
  • Strong comfort working with REST/JSON, scripting languages (Python or JavaScript), and modern dev tools (Git, NPM/PNPM).
  • Track record of ownership and grit — moments where you built something from scratch, solved hard problems, or exceeded expectations.
  • Excellent communication skills — you can explain complex AI concepts clearly to both technical and non-technical audiences.
  • Thrives in a fast-moving, high-intensity environment — motivated by challenge, curiosity, and the pursuit of great work.
  • Willingness to work in-person frequently (SF HQ and customer sites) to collaborate and accelerate learning.

Nice-to-Haves

  • Hands-on experience experimenting with or deploying LLM-powered tools or agents.
  • Prior startup or founder experience — you know what it takes to build without a playbook.
  • Curiosity about AI agent design, orchestration, and automation systems.
  • Experience working directly with customers to identify pain points and turn them into shipped solutions.
  • A portfolio of personal or side projects that showcase creativity, technical depth, and persistence.
  • Exceptional new grads with strong ownership and ambition are welcome to apply.

Why you'll love working here

You’ll be joining one of the fastest-moving AI teams in the world — where speed, creativity, and ownership are the default. You’ll ship real agents used by real customers, working directly with teams that are transforming how humans and AI collaborate.

This role is perfect for someone who loves building, learning, and pushing boundaries a hands-on candidate who wants to see their work in the wild, solving real problems for real people.

Relentlessness is the most important quality

  • If you think you’re missing relevant experience but you’re a fast learner who’s excited for a new challenge – and you have the intangibles our team is looking for – please reach out. As long as you’re resourceful and a fast learner (and you can prove it to our team) we would love to meet you.

Additional Information
Bland is an equal opportunity employer. We are committed to proving equal employment opportunities to all qualified applicants and employees and do not discriminate based on any legally protected characteristic.

Bland participates in the E-Verify employment verification program. All new hires are required to complete the Form I-9, and employment will be verified though E-Verify as part of the onboarding process.

Prep for this interview

5 questions likely to come up at Bland AI, each matched to a line in this posting.

  1. 1Discovery and scoping
    They wrote: “Own end-to-end delivery. From discovery call to deployment, you’ll lead the technical build, testing, and iteration — ensuring the experience feels natural, human, and on-brand.”

    A customer says “we want AI in our claims process.” What do you ask in the first meeting?

    How to answer

    Why they ask: Most FDE work starts this vague. They want to hear you find the real problem before you pick a tool.

    1. Map the current process: who touches a claim, in what order, with which systems
    2. Find the slowest or most error-prone step and ask what it costs them
    3. Agree on one measurable goal (for example time per claim, or error rate)
    4. Ask what data you can access, and who signs off on security

    Tip: Ask about the work, not the technology. Who does it today, how long it takes, what a mistake costs, and how they'd know it got better.

  2. 2Integrations and APIs
    They wrote: “Design and deploy AI solutions. Work closely with customers to translate their challenges into functional agents, integrating APIs and data sources to automate real business processes.”

    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.

    1. Find who owns the system and get read access to a test environment
    2. Watch real traffic or logs to learn the data shapes
    3. Build a thin adapter with logging around every call
    4. 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.

  3. 3LLMs, RAG and agents
    They wrote: “Hands-on experience integrating LLMs or AI SDKs into web applications.”

    How do you know an LLM feature is good enough to ship?

    How to answer

    Why they ask: Evals are what separate a demo from production. Many roles list them by name.

    1. Write 50–200 real examples with expected outcomes, with customer experts
    2. Agree on a pass bar and the errors that are never acceptable
    3. Score automatically where possible; review a sample by hand
    4. Re-run on every prompt or model change, and watch live traffic after launch

    Tip: Describe a test set built with the customer, a pass bar agreed up front, and checks that run on every change.

  4. 4Coding
    They wrote: “Strong comfort working with REST/JSON, scripting languages (Python or JavaScript), and modern dev tools (Git, NPM/PNPM).”

    Here's a CSV export from a customer. Write a script that cleans it and loads it into our API.

    How to answer

    Why they ask: Very close to real FDE work. They watch how you handle bad rows and failures.

    1. Read with a proper CSV parser; check the header first
    2. Validate each row and collect errors, not crash on the first one
    3. Send in batches with retries and a clear report at the end
    4. Write one or two quick tests for the parsing

    Tip: Talk through edge cases out loud: encodings, missing fields, duplicates, rate limits.

  5. 5Ownership and working with customers
    They wrote: “Track record of ownership and grit — moments where you built something from scratch, solved hard problems, or exceeded expectations.”

    Describe a time you had to tell a customer bad news.

    How to answer

    Why they ask: FDEs are the face of the company on site. Trust is part of the job.

    1. The situation and what went wrong
    2. When and how you told them
    3. The plan you offered
    4. How the relationship looked afterwards

    Tip: Pick a story where you told them early and came with a plan.

Not the one? Get the next one by email

New roles land here every day. Pick what you want to hear about.

FDE Info

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.

Similar roles at other companies

Bland AI

$120–200k · On-site

Apply