ML Engineer, Retrieval – Grounded Generation

atDefcon AIRemoteUS flagUnited StatesFull-timeMachine Learning EngineerMid-levelSenior$165k – $200k/year

Posted Oct 2

This is a fully remote position, open to applicants in United States.

📋 Description

• Develop embeddings, vector storage, and retrieval systems at scale utilizing a vast, provenance-tracked evidence base.

• Integrate language models to ensure generated text is linked to cited source records.

• Evaluate citation failures and assess grounding quality.

• Create prompts and output schemas.

• Manage model packaging, versioning, serving, and rollback processes.

• Implement telemetry for retrieval and generation quality, recommendation/version attribution, overrides, abstentions, grounding failures, latency, throughput, and measurement events.

• Provide bounded model assistance for complex narrative extraction, ensuring every output is connected to its source passage.

• Offer recorded rule context for every model-assisted step, including precise rule versions and ordered context.

• Sustain a modular in-boundary serving path, either self-hosted or managed, alongside the primary managed inference service.

• Produce generated explanations, scalable retrieval solutions, trustworthy rollback, and comprehensive measurement telemetry.


⛳️ Requirements

• Over 5 years of experience, including a production or near-production retrieval-augmented (RAG) system that you developed independently.

• Ability to discuss your retrieval design in detail, including the vector store utilized, rationale behind choices, grounding testing methods, practical citation failures, and rollback processes.

• Proficiency in Python, with practical experience in embeddings and vector retrieval at scale.

• Transparency regarding what was delivered in previous projects—whether it was a prototype, proposal, or deployed code—as this distinction is more significant than the title on a resume.

• US Citizenship is required.

• An active US Secret clearance is mandatory to start.

• Preferred: Experience with deploying models in restricted or air-gapped environments.

• Preferred: Operation of self-hosted or open-weight models.

• Preferred: Expertise in fine-tuning, adapters, or custom embeddings.

• Preferred: Familiarity with Federal DevSecOps, RMF, ATO, or DoW cloud environments.

• Preferred: An active Top Secret clearance.


🏝️ Benefits

• A fully remote, results-oriented work environment.

• Competitive salary, bonus, and equity package.

• Comprehensive health insurance for you and your family, fully employer-paid, including medical, dental, and vision coverage.

• Unlimited paid time off (PTO) with manager approval.

• A flexible work environment allowing you to manage your workday.

• 14 weeks of fully-paid parental leave.

People also viewed

Empower AI13 hours ago

AI/ML Engineer

US flagUnited States OnlyFull-timeMachine Learning Engineer$127.8k – $197.9k/year
ApplyView job
Augeo15 hours ago

Senior Machine Learning Engineer – Applied AI

US flagMinnesota OnlyFull-timeMachine Learning Engineer$150k – $200k/year
ApplyView job
Stack AV19 hours ago

Senior Staff Software Engineer, ML Training Infrastructure

US flagUnited States OnlyFull-timeMachine Learning Engineer
ApplyView job
Striveworks19 hours ago

Senior Machine Learning Engineer, Maritime Systems

US flagTexas OnlyFull-timeMachine Learning Engineer$160k – $200k/year
ApplyView job
SandboxAQ1 day ago

Senior Machine Learning Engineer – Medical Devices

US flagUnited States OnlyFull-timeMachine Learning Engineer$131k – $246k/year
ApplyView job
Weekday (YC W21)1 day ago

Machine Learning Engineer, Scientific Computing – AI Evaluation

US flagUnited States OnlyPart-timeMachine Learning Engineer$90 – $140/hour
ApplyView job

Never miss a great job!

Get handpicked remote jobs straight to your inbox weekly.

Trusted by 7,400+ designers