Apply

Ready to go for it?

AI Apply speeds things up—apply directly if you prefer.

FREE ACCESS
5,000–10,000 jobs/day
Scoutfield Logo

See all jobs on Scoutfield

Search thousands of fresh jobs every day.

Discover
  • Fresh listings
  • Fast filters
  • No subscription required
Create a free account and start exploring right away.
QED

AI Engineer

QED

. Design, build, and maintain AI systems that turn customer conversations and uploaded documents into grounded, auditable cost estimates .

Posted 10/30/2026full-timeRemote • United StatesMid-LevelSeniorWebsite

Core Competencies

Role fit
Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates expertise in building and maintaining LLM-powered systems, including retrieval-augmented generation and prompt/evaluation pipelines, while effectively communicating complex technical concepts to diverse stakeholders. Proven ability to lead AI workstreams, mentor engineers, and deliver scalable solutions under time pressure.

Highest-signal resume keywords
LLM-Powered Systems DevelopmentAI Development Tools FluencyRetrieval-Augmented Generation ExpertiseProduction Software Engineering SkillsTechnical Direction and Mentorship

ATS Keywords

Tailor your resume
Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills
Software EngineeringMachine Learning SystemsAgent DevelopmentCost EstimationData StructuresAPI DevelopmentVector SearchEmbedding TechniquesQuery RewritingSemantic Chunking
Soft Skills
Clear CommunicationLeadershipCritical Decision-MakingMotivationCollaboration
Tools & Technologies
AWS BedrockOpenAIVLLMPydanticObservability ToolsMiddlewareGraph State ManagementStreaming FlowsClient Meeting ToolsAsynchronous Communication
Certifications & Qualifications
Cloud CertificationMachine Learning Certification
Industry Keywords
AI SystemsCost EstimatesRetrieval QualityGroundingDocument ProcessingWork Breakdown StructureFast-Paced EnvironmentStakeholder SatisfactionAgent Reliability PatternsEvaluation Frameworks

Tech Stack

Tools & technologies
AWSCloudReact

About the role

Key responsibilities & impact
  • Design, build, and maintain AI systems that turn customer conversations and uploaded documents into grounded, auditable cost estimates
  • Build and maintain LangGraph agents, including ReAct retrieval sub-agents, custom middleware, Pydantic-typed graph state, and streaming flows
  • Own retrieval quality end to end through agentic retrieval, collection routing, LLM-driven metadata filters, similarity thresholds, query rewriting, semantic chunking, and citation tracking
  • Integrate AWS Bedrock, OpenAI, and self-hosted vLLM behind an abstract provider interface
  • Develop and maintain platform API services, relational and domain-knowledge data stores, vector stores, and observability/tracing for AI workflows
  • Set technical direction for the AI workstream
  • Review designs and code, mentor engineers, and align with product stakeholders
  • Improve agent task success rate, retrieval precision/recall, grounding and citation accuracy, groundedness, delivery, review quality, mentoring outcomes, and stakeholder satisfaction

Requirements

What you’ll need
  • Bachelor's degree in Computer Science, Software Engineering, Data Science, or Mathematics
  • Minimum of 6 years of progressive software engineering experience
  • At least 1 year building production LLM-powered or machine-learning systems, including agents, RAG, or prompt/evaluation pipelines
  • Proven delivery in a fast-paced environment
  • Availability to overlap U.S./Eastern-Time business hours for client meetings
  • Expert production software engineering skills
  • Expertise building LLM-powered systems, including agents/orchestration, retrieval-augmented generation, and prompt/evaluation pipelines
  • Fluency in using AI development tools to accelerate delivery
  • Deep understanding of retrieval and grounding, embeddings and vector search, multi-model integration, and cost/latency tuning
  • Ability to learn the cost-estimation / Work Breakdown Structure domain quickly
  • Ability to analyze complex, non-deterministic AI behavior from production traces and deliver scalable, well-tested solutions under time pressure
  • Exceptional ability to communicate technical and model-behavior concepts clearly to non-technical and client stakeholders
  • Confidence in live U.S./ET client meetings
  • Clear asynchronous written communication across time zones
  • Proven ability to make critical, time-sensitive decisions with limited information
  • High ownership, motivation, bias to action, and willingness to go the extra mile
  • Good leadership skills
  • Desirable: Master's degree in Computer Science, Machine Learning, or AI
  • Desirable: Relevant cloud or machine-learning certification
  • Nice to have: Self-hosted model inference, observability and tracing tooling, clean layered service architecture, internal AI tooling/automation, cloud-platform depth, agent-reliability patterns, multi-format document ingestion and processing, evaluation/benchmark frameworks, regression fixtures, U.S.-based client experience, mentoring, design reviews, technical direction, and AI roadmap trade-offs

Benefits

Comp & perks
  • Flexible ways of working
  • Long-term development opportunities
  • Collaboration-focused, trust-based work environment
  • Autonomy with accountability
  • Meaningful ownership and influence over architecture, technical direction, and standards
  • Mentoring and growth alongside experienced engineers
  • Sustainable working practices