• Build and optimize LLM serving and inference systems for production environments • Improve performance across GPU and CPU pathways • Work on KV cache, memory, storage, and throughput bottlenecks • Design and scale systems that support RAG and retrieval-heavy AI workloads • Contribute to infrastructure where storage architecture and systems efficiency materially affect AI performance • Solve engineering problems at the intersection of AI, high-performance systems, and distributed infrastructure

Role Description We’ve built an AI-native internal platform that powers every aspect of our Amazon brand management business. AI isn’t a feature — it’s the backbone. - LLMs classify and respond to inbound communications - AI generates pre-call intelligence briefs from raw enrichment data - A RAG system feeds context into every generation pipeline - An AI checkpoint system audits all generated content against quality gates The platform is already live and scaling fast: - 17+ background services - 130+ frontend pages - 214 backend services - 184 database tables - Dozens of autonomous AI pipelines We’re hiring an engineer who operates at the intersection of AI and production systems. You’ll build, optimize, and scale AI-powered infrastructure across the full stack. What You’ll Build & Scale - AI Communication Pipelines - Classify inbound messages by category, intent, urgency, and tone - Generate contextual responses using enrichment data - Implement human approval gates - AI-Powered Sales Intelligence - Transform raw enrichment data into structured pre-call briefs - Generate: background, pain hypotheses, talking points, rapport hooks - RAG System - Vector database with embeddings - Markdown-aware chunking - Async ingestion workers - Semantic search API - Trend Intelligence Engine - Process RSS feeds, social media, video platforms, and search trends - Generate reports, forecasts, and content drafts - Run autonomously on scheduled jobs - Content Quality Pipeline - Multi-agent system (outline → audit → generate) - Binary quality gates (PASS/FAIL with citations) - Supports multiple content formats - Automated Lead Qualification - Enrich leads with product data and market insights - AI scoring and qualification grading - Automated audit reports - AI Executive Assistant - Slack operations - Scheduling workflows - Email triage and follow-ups Qualifications - Production LLM experience (Claude/OpenAI in real systems) - RAG system experience (embeddings, retrieval, chunking, context handling) - 3+ years TypeScript / Node.js - Strong React skills - PostgreSQL (queries, migrations, indexing) - API integrations (REST, OAuth, webhooks) - Linux server experience (SSH, logs, debugging, deployments) Requirements - Strong Pluses - Multi-agent LLM systems - Anthropic Claude expertise - Vector search / embeddings - Slack API experience - Ad platform APIs (Meta, Google, LinkedIn) - LLM observability (cost, tracing, monitoring) - Amazon / eCommerce experience - AI-assisted dev tools (Cursor, Claude Code, etc.) Benefits - Competitive salary based on experience - High-impact role with strong ownership - Opportunity to scale cutting-edge AI systems to world-class level

Role Description We are seeking an AI Developer with strong expertise in Generative AI, Large Language Models (LLMs), and prompt engineering to design, build, and optimize intelligent systems. The ideal candidate will have hands-on experience with multi-agent architectures, LLM orchestration, and production-grade AI deployments. Qualifications - Strong programming skills in Python (preferred) or similar languages - Deep understanding of prompt engineering techniques and patterns - Experience working with OpenAI, open-source LLMs, or similar platforms - Familiarity with vector databases and embeddings (e.g., Pinecone, FAISS) - Knowledge of multi-agent architectures and orchestration strategies - Understanding of AI evaluation metrics and model performance tuning Requirements - Design, develop, and deploy applications powered by LLMs and generative AI models - Engineer, test, and optimize prompts for performance, accuracy, and reliability - Build and manage multi-agent systems for complex task orchestration - Integrate AI models with APIs, databases, and external tools - Implement retrieval-augmented generation (RAG) pipelines - Fine-tune and evaluate models using domain-specific datasets - Monitor model outputs, ensure alignment, and reduce hallucinations - Collaborate with product, data, and engineering teams to deliver AI-driven features Benefits - Experience with fine-tuning LLMs or training custom models - Knowledge of cloud platforms (AWS, GCP, Azure) - Exposure to conversational AI, chatbots, or copilots - Understanding of AI safety, guardrails, and governance

Role Description BME Strategies is seeking a Junior Engineer, AI to help design and build AI-powered tools that advance our public health capabilities. Reporting to the AI Committee Lead, you'll work across multiple cloud platforms and AI ecosystems to develop real solutions to real problems. This is a hands-on role ideal for someone who loves building things and wants their work to make a lasting impact. This role will translate emerging AI technologies into practical tools that help our team work smarter and serve clients better. Key Responsibilities - AI Tool Development [70%] - Build and deploy internal AI-powered applications and automation tools across multiple platforms, including Google Cloud Platform (GCP), AWS, Azure, and/or Anthropic/OpenAI APIs. - Design and build external-facing applications, such as chatbots, tailored to client needs, delivering AI-powered solutions that directly support public health programs and government operations. - Develop tools that collect, aggregate, and analyze data from our existing sources, replacing manual processes with intelligent automation. - Design and implement retrieval-augmented generation (RAG) pipelines to power intelligent, context-aware internal tools. - Experiment with and integrate large language models (LLMs), AI agents, and emerging frameworks to solve operational and public health challenges. - Build lightweight internal-facing apps and dashboards using tools like AppScript, or similar. - Communication & Collaboration [20%] - Partner with AI Committee Lead to translate client or end-user public health needs into concrete technical requirements and measurable AI solutions. - Translate technical workflows and concepts clearly for non-technical stakeholders. - Collaborate closely with the AI Committee and program teams to identify and prioritize high-impact opportunities. - Present findings, recommendations, and project updates to leadership and relevant project teams. - Research & Quality [10%] - Research emerging AI models and platforms and help select the right tools for specific use cases. - Implement testing and quality assurance frameworks to ensure AI accuracy and reliability. - Monitor the performance, cost, and reliability of deployed AI models and systems, implementing optimizations as needed. - Establish and maintain documentation and best practices across AI tooling. Qualifications - 1 year of relevant experience and a Bachelor's degree required; recent college graduates encouraged to apply. - 1+ years of internship-level, undergraduate coursework-related, or professional experience building AI/ML applications or related software engineering roles. - Strong Python (or similar) programming skills. - Proven experience designing and implementing retrieval-augmented generation (RAG) systems. - Hands-on experience with at least one major cloud platform (GCP, AWS, or Azure). - Experience with vector databases, including open-source solutions, and cloud-native vector search offerings. - Experience working with LLM APIs (OpenAI, Anthropic Claude, Gemini, etc.). - Familiarity with Google AppScript or similar automation tools. - Experience testing LLM outputs for accuracy, reliability, and performance. - Strong communication skills with non-technical audiences. - Ability to work independently and as part of a team in a fast-paced remote consulting environment. - Alignment with BME’s shared values. Preferred - Experience with frameworks like LangChain, LlamaIndex, or similar. - Familiarity with MLOps tools and practices for deploying, monitoring, and managing models in production (e.g., Docker). - Experience writing production-level SQL and working with data warehousing solutions (e.g., BigQuery, Snowflake). - Experience with data privacy tools such as Google DLP. - Interest in or experience within public health, healthcare, or government sectors. - Experience with projects that connect public health and tech is strongly preferred. - Optimistic and solution-focused. - Ability to concisely summarize technical ideas. Work Environment BME Strategies is a remote-first organization; this is a full-time position based in a home office environment within the U.S. Compensation & Benefits - 6+ weeks total leave, including paid vacation, sick time, personal leave, and floating holidays; - Health, dental, and vision insurance, with 75% employer-paid coverage for the employee & 50% employer-paid coverage for dependents; - Health FSA and dependent care FSA; - 401(k) with employer match; - Employer-paid short-term and long-term disability insurance; - One-time technology stipend; - Opportunities for professional development and career growth. - The salary range for this position is $70,720 - $83,200 annually. How to Apply To apply for this position, please complete and submit all information in the application link. We expect a large volume of applicants for this position and only those candidates invited to move forward in the interview process will be contacted. Important Notice on Recruitment Fraud: BME Strategies communicates with applicants only through email addresses ending @bmestrategies.com. We do not use third-party domains for recruitment outreach. If you receive communication from a different email address, please do not respond and report it to us at info@bmestrategies.com. Please note that BME Strategies is unable to sponsor work-related visas. BME Strategies is made up of individuals with different strengths, experiences, and backgrounds. Diversity not only includes race and gender identity but also age, disability status, veteran status, sexual orientation, religion, and many other parts of one’s identity. These varied points of view are key to our success, and inclusion is everyone's responsibility. BME Strategies is an equal opportunity employer. All qualified applicants will be considered for employment without unlawful discrimination based on race, color, creed, national origin, sex, age, disability, marital status, sexual orientation, military status, prior record of arrest or conviction, or current employment status.