Arlington, United States · hace 3 meses
Diseñar y construir aplicaciones web full-stack y APIs, e integrar capacidades de LLM/GenAI, como pipelines RAG, en una plataforma empresarial segura de conocimiento.
**Secret OR Top Secret Clearance Required** We are seeking a highly skilled Full Stack Developer with strong software design expertise to design, build, and scale modern applications that integrate data-intensive systems and Generative AI capabilities. This role sits at the intersection of software engineering, data engineering, and AI innovation, supporting the development of enterprise solutions that leverage large datasets and advanced language models. PixelRain AI is a small, fast-moving AI company delivering an AI-powered product-lifecycle knowledge platform for a U.S. Department of War (DoW) customer: governed ingestion of technical documents, an enterprise ontology and knowledge graph, and generative-AI applications that draft maintenance-planning products and answer engineering questions with citations — running in the customer's cloud environment, with an offline variant for disconnected use. Small team, real users, working software demonstrated every sprint.. You will work closely with cross-functional teams to architect, develop, and deploy scalable applications, while helping drive the integration of LLM/GenAI technologies into production environments. Accepting all skill levels: salary based on skill level and technical competencies Salary: 105,000 - 180,000 Key Responsibilities Full Stack Development • Design, develop, and maintain end-to-end web applications (front-end, back-end, and APIs) • Build scalable backend services using Python frameworks (e.g., Flask, FastAPI, Django) • Develop responsive, user-friendly front-end interfaces using modern frameworks (React, Angular, or similar) • Architect and implement RESTful and/or GraphQL APIs • Ensure application performance, scalability, and security across the stack Database & Data Engineering • Design, develop, and optimize relational and/or NoSQL database systems • Create efficient data models and schemas to support large-scale applications • Develop scripts and pipelines to ingest, transform, and manage data flows • Troubleshoot performance bottlenecks and ensure data integrity • Work with large, complex datasets to enable analytics and AI use cases Generative AI / LLM Integration • Build, test, and deploy LLM-powered applications and workflows • Integrate Generative AI capabilities into existing platforms and user experiences • Evaluate and assess LLM outputs for performance, accuracy, and usability • Implement Retrieval-Augmented Generation (RAG) pipelines and vector database integrations • Support fine-tuning, prompt engineering, and optimization of models for mission-specific use cases System Design & Architecture • Contribute to the design of scalable, distributed system architectures • Collaborate with engineers to integrate AI components into enterprise environments • Balance tradeoffs between performance, cost, and scalability • Support CI/CD pipelines and DevSecOps best practices for deployment Client & Mission Support • Translate ambiguous requirements into technical solutions • Help stakeholders understand evolving AI/technology options • Provide guidance on best practices for integrating AI into business workflows Requirements Required Qualifications • 7+ years designing, building, and shipping full-stack web applications. • Hands-on AWS experience — compute, storage, IAM, OpenSearch or similar (GovCloud experience a plus). • Strong Python and modern JavaScript; comfortable owning a feature across the stack. • Real experience building with LLMs and GenAI: RAG, embeddings, prompt design, and model APIs — not just using chat tools. • Systems-integration experience: REST APIs and data exchange with enterprise systems. • Strong experience developing Python applications from scratch, including testing and deployment • Hands-on experience with full stack development (front-end + back-end) • Proficiency with database design and management (SQL and/or NoSQL) • Experience with data wrangling, transformation, and scripting for data pipelines • Familiarity with using LLMs (e.g., ChatGPT or similar) to enhance development workflows • Experience building and consuming APIs • Understanding of software development best practices (version control, testing, CI/CD) Preferred / Nice-to-Have Qualifications • Experience deploying and managing LLMs locally and in AWS environments • Hands-on experience with fine-tuning models and integrating them into production systems • Experience building RAG solutions and working with vector databases (e.g., Pinecone, FAISS) • Knowledge of prompt engineering and content filtering techniques • Familiarity with frameworks such as LangChain, LlamaIndex, or OpenAI function calling • Experience with model distillation and optimization • Exposure to knowledge graphs and graph databases (e.g., Neo4j) • Experience working in cloud environments (AWS, Azure, or GCP) Benefits InterImage is an Equal Opportunity Employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, age, disability or veteran status, or any other applicable state or federal protected class. InterImage provides affirmative action in employment for qualified Individuals with a Disability and Protected Veterans in compliance with Section 503 of the Rehabilitation Act and the Vietnam Era Veterans’ Readjustment Assistance Act.
Publicada el 26 jul 2026
