Generative AI Applications Engineer (Agents & RAG)
RemoteHunter · United States
- Hybrid
- Full-time
- $150,000 / year
- United States
Job highlights
- Develop production generative AI for federal programs.
- Focus on agentic workflows and retrieval-augmented generation.
- Integrate with major cloud AI platforms.
- Ensure production rigor and safety compliance.
- Requires Python and U.S. Citizenship.
About the role
About Our Client
The organization operates in the federal technology sector, supporting clients across defense, national security, public safety, civilian, and military health agencies. It addresses the challenge of delivering secure, reliable, and scalable technology solutions that enhance mission effectiveness and public service. With a workforce of over 13,000 people, the organization focuses on applying advanced technology and innovation to strengthen national security and improve government operations.About the Opportunity
The Generative AI Applications Engineer (Agents & RAG) role is focused on developing and deploying production-grade generative AI applications tailored for confidential federal programs. This position converts mission requirements into secure, scalable AI solutions without model training, covering agentic workflows, retrieval-augmented generation (RAG), prompt and policy design, large language model (LLM) evaluation, and platform integration. The engineer takes full ownership from evaluating use cases through deployment and operational excellence, collaborating with product, security, data, and site reliability teams to ensure safe and efficient delivery.Responsibilities
- Design and deploy mission-grade generative AI workflows and RAG systems with low hallucination, low latency, and controlled cost
- Apply agent frameworks and orchestration patterns to manage tasks, tools, guardrails, and fallback strategies
- Integrate with cloud AI platforms and managed services without model training (AWS Bedrock, Azure OpenAI, Google Vertex AI, Amazon Kendra, etc.)
- Select and evaluate LLMs based on quality, safety, latency, and cost; develop and test prompts and policies; ensure observability and safe rollback
- Build and optimize retrieval pipelines and vector search systems (Pinecone, Weaviate, OpenSearch, pgvector, FAISS/Chroma) for effective data grounding
- Maintain production rigor through metrics, logging, tracing, A/B testing, incident playbooks, and safety compliance
- Define and manage service level indicators and objectives; participate in on-call rotations and postmortems; optimize usage and costs
- Develop reusable platform components including SDKs, CI/CD templates, and infrastructure-as-code modules
- Deliver solutions in complex environments with zero trust principles and audit-ready controls, including hybrid, restricted, or air-gapped settings
Requirements
- Experience owning end-to-end production systems including integration, deployment, observability, and incident response
- Hands-on experience with LLMs, transformer-based applications, and RAG in production
- Proficiency in Python programming
- Experience with vector search and retrieval technologies and grounding AI in enterprise or mission data
- U.S. Citizenship
Pay Range and Compensation Package
- The pay range for this position in specified locations is $103,200—$203,400 USD
- Compensation varies based on location, role, skills, and experience
Equal Opportunity Statement
Our client is an equal opportunity employer. They celebrate diversity and are committed to creating an inclusive environment for all employees. All qualified applicants will receive consideration for employment without regard to race, color, religion, gender, gender identity or expression, sexual orientation, or national origin.Note
RemoteHunter is not the Employer of Record (EOR) for this role. Our purpose in this opportunity is to connect exceptional candidates with leading employers. We help job seekers worldwide discover roles that match their goals and guide them to complete their full application directly through the hiring company’s career page or ATS.Key skills/competency
Generative AI Applications Engineer, Agents, RAG, LLMs, Python, Vector Search, Cloud AI Platforms, Production Systems, Federal Technology, Mission RequirementsSkills & topics
- Generative AI
- Applications Engineer
- Agents
- RAG
- LLM
- Python
- Vector Search
- Federal Technology
- AI Engineer
- Machine Learning
How to get hired
- Tailor your resume: Highlight experience with LLMs, RAG, Python, and production systems. Emphasize federal sector or security-conscious environments.
- Showcase your projects: Detail end-to-end ownership of AI applications, including integration, deployment, and observability.
- Address requirements directly: Clearly state your U.S. Citizenship and any experience with cloud AI platforms or vector search technologies.
- Prepare for technical questions: Be ready to discuss agent frameworks, RAG systems, LLM evaluation, and production deployment strategies.
- Understand the mission: Research the federal technology sector and how AI can enhance mission effectiveness for defense and security agencies.
Technical preparation
Master Python for AI application development.,Build and deploy RAG systems.,Practice with vector databases.,Familiarize with cloud AI platforms.
Behavioral questions
Describe owning an end-to-end production AI system.,How do you ensure low hallucination and latency?,Discuss a time you handled AI incident response.,How do you balance AI quality, cost, and safety?
Frequently asked questions
- What is the primary focus of the Generative AI Applications Engineer role at RemoteHunter's client?
- The Generative AI Applications Engineer role focuses on developing and deploying production-grade generative AI applications, specifically utilizing agentic workflows and retrieval-augmented generation (RAG), for confidential federal programs.
- What technical skills are essential for this Generative AI Applications Engineer position?
- Essential technical skills include hands-on experience with LLMs, transformer-based applications, RAG in production, proficiency in Python, and experience with vector search and retrieval technologies.
- Does this Generative AI Applications Engineer role require U.S. Citizenship?
- Yes, U.S. Citizenship is a mandatory requirement for this Generative AI Applications Engineer position, as it involves working with confidential federal programs.
- What kind of AI platforms will the Generative AI Applications Engineer integrate with?
- The engineer will integrate with major cloud AI platforms and managed services such as AWS Bedrock, Azure OpenAI, Google Vertex AI, and Amazon Kendra, without requiring model training.
- What is expected in terms of production rigor for this Generative AI Applications Engineer role?
- Production rigor is critical, involving metrics, logging, tracing, A/B testing, incident playbooks, safety compliance, defining service level objectives, and participating in on-call rotations and postmortems.
- Can I apply for the Generative AI Applications Engineer role if I am not a U.S. Citizen?
- No, U.S. Citizenship is a firm requirement for this Generative AI Applications Engineer position due to the nature of the federal programs involved.
- What is RAG, and how is it used in this Generative AI Applications Engineer role?
- RAG stands for Retrieval-Augmented Generation. In this role, it's used to ground generative AI responses in enterprise or mission data, improving accuracy and reducing hallucinations by retrieving relevant information before generating an answer.
- What is the salary range for the Generative AI Applications Engineer position?
- The pay range for this Generative AI Applications Engineer position is $103,200 to $203,400 USD, with compensation varying based on location, role, skills, and experience.