Lead AI Developer

Jahnel Group's mission is to provide the absolute best environment for software creators to pursue their passion by connecting them with great clients doing meaningful work.

We get to build some of the most complex and compelling applications for our clients located across the country. We're a fast-growing INC 5000 recognized company, yet we still work as a very close-knit team (100+ employees). We're growing like crazy, and if you're looking for the next place to call home, hit us up for a beer or coffee. 

We're in search of a Lead AI Developer with deep AI/LLM expertise to join our team right away to architect and build an innovative AI-powered content creation platform for a major publishing client. This is a high-impact, fast-paced project where you'll work directly with a Technical Principal, client stakeholders, and a cross-functional Agile team.

This role requires someone who can move quickly, make smart architectural decisions under pressure, work collaboratively in pair programming sessions, and balance technical excellence with pragmatic delivery. You'll be building the core AI engine and backend infrastructure that powers complex, stateful content workflows.

We value problem-solving prowess and thrive on creative and innovative thinking.

Instead of the typical job description, here's a breakdown of tasks and qualities we're looking for in our potential team member:

• Design and implement scalable backend architecture for AI-assisted content generation workflows
• Build and optimize LLM integration layers with focus on prompt engineering, context management, and token efficiency
• Architect data models for complex, stateful content management across long-form narratives
• Make real-time technical decisions balancing performance, cost, and feature requirements
• Collaborate with Technical Principal on system design and infrastructure decisions
• Integrate and optimize OpenAI GPT-4 and/or AWS Bedrock LLM APIs for content generation
• Design prompt architectures that handle complex branching logic and narrative coherence
• Implement context window management strategies for long-form content tracking
• Build API metering and cost tracking systems to monitor token consumption and optimize unit economics
• Develop versioning and state management systems for AI-generated content edits
• Build RESTful APIs and backend services on AWS infrastructureIntegrate with existing client systems including e-commerce and subscription 
  platforms
• Implement authentication, authorization, and data security best practices
• Design database schemas and data persistence strategies for complex content structures
• Set up CI/CD pipelines, monitoring, and logging infrastructure
• Participate in daily pair programming sessions with other developers and designers
• Lead technical discussions in daily standups, sprint planning, and retrospectives
• Deliver working software in 1-2 week sprints with weekly client demos
• Task-switch efficiently as priorities shift based on client feedback and technical discoveries
• Mentor junior developers and share knowledge with the broader team

• 7+ years of software engineering experience building production web applications
• Deep expertise in AI/LLM development - hands-on experience building applications with OpenAI, Anthropic, or AWS Bedrock APIs
• Proven experience with prompt engineering, context window management, RAG systems, and AI cost optimization
• Strong backend development skills - API design, database architecture, distributed systems
• Deep expertise in designing and building systems on AWS - Lambda, ECS, RDS, S3, CloudWatch, etc.
• Experience with Agile/Scrum methodologies and iterative development practices
• Pair programming experience - comfortable working synchronously with other developers
• Ability to task-switch rapidly and reprioritize in fast-moving, high-stakes environments
• Excellent communication skills - can explain complex technical concepts to non- technical stakeholder
• Languages: Python, Go, , or similar backend languages
• AI/LLM: OpenAI API, AWS Bedrock, LangChain, semantic search, vector databases
• Cloud: AWS services (Lambda, ECS, RDS, DynamoDB, S3, API Gateway, CloudWatch)
• Infrastructure: Terraform or CloudFormation, Docker, CI/CD pipelines
• Databases: PostgreSQL, DynamoDB, Redis, or similar
• APIs: RESTful design, GraphQL, WebSocket connections
• Testing: Unit testing, integration testing, test automation frameworks

• Latin America
• 100% Remote

Other Information 

The work hours will be approximately 9:00 am to 5:00 pm EST, depending on workload, with the occasional late night when a tight deadline calls for it. We work for security-conscious clients, thus background checks will be required. Salary dependent upon experience.