Senior Applied AI Engineer - Production ML & Solutions

Groundswell

Utah

On-site

USD 150,000 - 205,000

Full time

2 days ago

Be an early applicant

Application generator

Turn this role into an interview — a resume and cover letter built around what this employer wants.

Get past ATS filters

Benefits offered by this job

Medical, dental, vision plans

401K with 4% match

Flexible Spending Account

Paid Time Off

Tuition reimbursement and professional

Flexible work schedule

On-site gym and childcare

Job summary

Groundswell is seeking an experienced engineer to translate ambiguous business problems into working AI solutions. You will engage with stakeholders, design approaches, build end-to-end capabilities, and own production deployment across discovery, build, and operations.

You will balance modern AI capabilities with engineering rigor, maintain governance, and deliver measurable outcomes for federal-facing engagements.

Qualifications

7+ years building and shipping production software.
2+ years hands-on experience building applications that integrate large language models, including prompt engineering, retrieval-augmented generation, structured extraction, tool use, and agent patterns.
Experience evaluating AI system quality with test sets, defining metrics, and making deployment decisions based on evidence.
Strong programming ability in Python, TypeScript, or SQL, with experience integrating APIs and working with imperfect data across the full application rather than the AI layer.
Proven ability to lead requirements conversations with non-technical stakeholders and translate what you hear into a technical approach.
Sound judgment on tradeoffs between accuracy, cost, latency, and complexity, with the ability to explain those tradeoffs to both engineers and executives.
Excellent written communication for client-facing documentation and design rationale.
Ability to work with minimal direction in ambiguous situations, surfacing problems worth solving before they are assigned, proposing an approach, and driving it to a decision.
A track record of improving the capability of other engineers, with or without a formal leadership title. U.S Citizenship required. Ability to obtain and maintain any federal government background investigation, suitability determination, or security clearance required by assigned client engagements.

Responsibilities

Lead discovery with business and technical stakeholders to understand the workflow, the decision being supported, and the current standard for acceptable results.
Define measurable success criteria before building, including accuracy targets, human review thresholds, acceptance conditions, and the definition of failure.
Recommend against AI when a simpler solution is the right one. Rules, process changes, and improved interfaces are often the correct answer, and identifying that early is part of the job.
Select the AI pattern appropriate to the problem, such as extraction, classification, summarization, retrieval, or an agentic workflow, rather than defaulting to the most sophisticated option available.
Make and defend architecture decisions on where a workload should run, weighing quality, cost, latency, security, and authorization constraints.
Build the complete capability rather than the AI components alone. This includes prompt and retrieval design, structured outputs, tool and function definitions, API integration, data handling, error states, and the user interface.
Build evaluation sets from real data and measure against them, iterating based on results rather than intuition.
Determine when a capability is ready for deployment, and identify when it is not.
Operationalize capabilities in the client environment, including governance, logging, and traceability requirements.
Produce clear documentation covering what the solution does, its known limitations, how it was validated, and what happens when it produces an incorrect result.
Monitor quality, cost, latency, and drift after launch, and optimize as better or less expensive options become available.
Set the direction clients cannot yet articulate. Show them what is possible, shape the roadmap, and support the case with working proof rather than presentation material.
Raise the technical level of the people around you by mentoring engineers newer to AI, reviewing their work, and building the team's judgment as well as its output.
Contribute reusable patterns back to the team so that each project does not start from scratch.
Move between client delivery, internal product work, rapid proofs of concept, and internal enablement as the work requires.