
Forward Deployed AI Engineer (Senior)
Posted Sep 11, 2026
The role in short
Design, build, and deploy production agentic AI systems directly within client environments, focusing on document intelligence, compliance, and operational workflows.
About AZX
Our mission is to accelerate positive impact in critical industries through AI transformation.
We’re growing quickly and already work with category-leaders in real estate (CBRE), energy (LevelTen Energy), logistics (Flexe) and utilities.
We’re a public benefit corporation, founded in 2024 and have been profitable from inception.
We work on challenges in clean energy, decarbonization, climate risk, energy systems and global economics. We’re building our company for long term success and aim to build the ultimate place to work if you’re passionate about AI and positive impact.
About the Role
We are seeking a Forward Deployed Engineer to join a team that scopes, builds, deploys, and measures AI systems inside client environments — utilities, commercial real estate, and logistics. Your software runs in the client's cloud, under their identity provider and toolchain, inside their compliance framework, integrated with their systems of record — you bring the right mix of models and tools for the job rather than working around it. The work is agentic AI with a correctness envelope: think document intelligence with deterministic, auditable validation where money or compliance is on the line, voice-of-customer AI, cognitive digital twins of a client's customers, and human-in-the-loop agentic workflows, all measured against real before/after baselines rather than left as shelf-ware. You won't be handed a finished spec — you'll sit with the client's operators and executives to find the real problem, design the solution with their architects, build it with your pod, and prove it worked with numbers both companies stand behind. You bring a strong area of expertise and expect to use it, and work closely with our team across DevOps, infrastructure, data pipelines, front end, and back end as the engagement requires — you are the engineering face of AZX.
Responsibilities:
- Own your client's technical delivery end to end — discovery support, solution design, build, deployment into the client's environment, and a handover their team can actually run.
- Build the trust machinery behind every system you ship: eval harnesses, replay loops, guardrails, cost/latency budgets, monitoring, and a defined "what happens when it's unsure" path.
- Extract structured facts from messy documents (like contractor bids or engineering forms) and build the deterministic checks that gate money- or compliance-sensitive answers, making "cannot determine" fail closed rather than open.
- Optimize pipelines for cost and quality — for example, moving a step from a frontier model to a fine-tuned small model or a deterministic rule, then proving quality held with a replay harness.
- Design and ship high-stakes systems like after-hours voicemail triage, defining the right autonomy boundary for the risk involved.
- Agree on and track the measurement story with the client — KPIs, baselines, and instrumentation for cost, performance, and quality — in writing before deployment and validated after.
- Maintain client-facing engineering presence: working sessions with their IT/security teams, demos, POCs that derisk the next engagement, and a feedback loop that carries field-learned requirements back to the platform team.
Core Qualifications:
- 5 + years of full-stack delivery skills: Python/FastAPI backends, React/TypeScript front ends, deployment, monitoring, real test coverage, and careful data handling since your pod is the whole team..
- Experience shipping LLM/agentic systems to production users, not prototypes, with structured outputs, tool use, retrieval, guardrails, and an eval loop you can defend to a skeptic.
- A well-stocked technical toolkit and the judgment to use it: small task models (OCR, ASR, classification, reranking), classical NLP, fine-tuning/distillation, deterministic rules, caching, and a frontier model only where it earns its cost.
- Experience deploying inside someone else's cloud, identity provider, repos, and compliance regime, and negotiating their IT constraints without losing the design.
- Strong stakeholder skills; running discovery with front-line operators, delivering executive readouts, and pushing back plainly (with a cheaper or safer alternative already sketched) when the ask is wrong.
- Comfort with ownership under ambiguity given a vague problem and a deadline, you return with a working thing or a good question
- Practical fluency across our stack Python (async/FastAPI/Pydantic), TypeScript/React, Postgres/pgvector, Redis, LLM provider APIs, RAG/hybrid retrieval, and agent frameworks (LangGraph/AutoGen/CrewAI-class or hand-rolled loops).
- Familiarity with enterprise deployment concerns: Docker, Terraform/Bicep, Azure and/or AWS, enterprise SSO (SAML/OIDC, Entra), and observability/cost tracking.
- A track record with enterprise integrations (SharePoint, Salesforce, SAP/ERP-class systems)
- Domain exposure to utilities, commercial real estate, or logistics is a plus
- Bachelor's Degree; Master's is a plus
Why AZX!
- Be part of a fast-growing, profitable, mission-driven company with industry-leading clients tackling the massive opportunity of AI transformation in critical industries.
- Competitive early-stage startup compensation (based on capabilities, experience, and location)
- Bonus eligibility
- Health insurance with meaningful coverage for dependents
- Flexible paid time off
- Equity
- Fully remote culture with a cluster of teammates in Seattle
Additional Information:
- Must be willing to travel to Seattle area for final interview and travel 2x/year for company summits
- Applicants must be currently authorized to work in the United States on a full-time basis.
- We are unable to sponsor or take over sponsorship of employment visas at this time.
- Please note that our interview process includes a live two-hour technical session with our engineering team, so if that format isn't a good fit, we'd ask that you not apply
Next Steps:
If this job sounds like a great fit but don’t check ALL of these qualification boxes, we’d still love to hear from you!
Prep for this interview
5 questions likely to come up at AZX, each matched to a line in this posting.
- 1LLMs, RAG and agents
They wrote: “Experience shipping LLM/agentic systems to production users, not prototypes, with structured outputs, tool use, retrieval, guardrails, and an eval loop you can defend to a skeptic.”
A customer wants a chatbot over their internal documents. How do you build it?
How to answer
Why they ask: RAG is the most common first project. They want the whole path, from messy files to answers people trust.
- Collect and clean the documents; handle permissions per user
- Split them into chunks, embed, and store with source links
- Retrieve, then answer with citations; say “I don't know” when retrieval is weak
- Build a test set of real questions with expected answers before launch
Tip: Spend more time on the data and on testing than on the model.
- 2Discovery and scoping
They wrote: “Strong stakeholder skills; running discovery with front-line operators, delivering executive readouts, and pushing back plainly (with a cheaper or safer alternative already sketched) when the ask is wrong.”
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.
- Map the current process: who touches a claim, in what order, with which systems
- Find the slowest or most error-prone step and ask what it costs them
- Agree on one measurable goal (for example time per claim, or error rate)
- 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.
- 3Coding
They wrote: “5 + years of full-stack delivery skills: Python/FastAPI backends, React/TypeScript front ends, deployment, monitoring, real test coverage, and careful data handling since your pod is the whole team..”
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.
- Read with a proper CSV parser; check the header first
- Validate each row and collect errors, not crash on the first one
- Send in batches with retries and a clear report at the end
- Write one or two quick tests for the parsing
Tip: Talk through edge cases out loud: encodings, missing fields, duplicates, rate limits.
- 4Ownership and working with customers
They wrote: “Comfort with ownership under ambiguity given a vague problem and a deadline, you return with a working thing or a good question”
Tell me about a project where the requirements kept changing. What did you do?
How to answer
Why they ask: Ambiguity is the norm. They want proof you can keep moving without a clear spec.
- The project and why requirements kept moving
- What you did to pin them down (short demos, written decisions)
- The trade-offs you made to keep shipping
- The result, with a number if you have one
Tip: Show how you reduced the change, beyond how you coped with it.
- 5Integrations and APIs
They wrote: “Familiarity with enterprise deployment concerns: Docker, Terraform/Bicep, Azure and/or AWS, enterprise SSO (SAML/OIDC, Entra), and observability/cost tracking.”
How would you set up single sign-on for a large customer?
How to answer
Why they ask: SSO (SAML or OAuth/OIDC) is a common first task in enterprise deals and a common source of delays.
- Confirm their identity provider (Okta, Entra ID, Google) and protocol
- Exchange metadata and test in a staging tenant first
- Map user groups to roles in your product
- Plan for user removal: what happens when someone leaves the company
Tip: Mention the people involved, and the protocol second. The customer's identity team usually controls the timeline.
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.