Chuck Babb

Building AI-powered workflow automation across Atlassian products using LLMs, prompt engineering, agentic AI, MCP, custom tools, and scalable backend integrations across Jira, Confluence, and enterprise systems.

• Built AI-assisted Jira workflows that convert natural-language requests into structured issues, implementation plans, task breakdowns, and recommended actions using Python, FastAPI, TypeScript, LLM APIs, structured outputs, prompt engineering, and microservice-based backend services.
• Developed an enterprise knowledge assistant across Jira and Confluence that retrieves relevant tickets, project documentation, and engineering context before generating grounded responses using semantic search, vector embeddings, retrieval pipelines, Python, PostgreSQL, Redis, OpenSearch, and AWS services.
• Built agentic workflow automation where AI agents understand user intent, maintain workflow state, select custom tools, collect context, and execute multi-step actions across Jira, Confluence, GitHub, and internal services using Python, FastAPI, TypeScript, asynchronous APIs, event-driven architecture, and microservices.
• Developed custom tools and MCP integrations for issue search, document lookup, dependency analysis, engineering context retrieval, workflow actions, and internal service access using MCP servers, REST APIs, JSON Schema, OAuth, TypeScript, Python, and backend tool registries.
• Built backend integration layers that allow agents to work through existing enterprise APIs, authorization rules, and business logic rather than directly accessing application databases, using API gateways, service-to-service authentication, REST/GraphQL APIs, PostgreSQL, Redis, and distributed backend services.
• Built reusable prompt and agent orchestration infrastructure for managing system prompts, dynamic context, model configuration, function calling, tool discovery, conversation state, and structured responses across multiple customer-facing AI products.
• Developed full-stack AI product experiences using React, Next.js, TypeScript, JavaScript, Python, FastAPI, Node.js, HTML/CSS, connecting frontend workflows to distributed AI and application services.
• Deployed AI backend workloads using Docker, Kubernetes, AWS ECS/EKS, Lambda, S3, SQS, CloudWatch, Redis, PostgreSQL, with horizontally scalable services supporting asynchronous AI processing.
• Built event-driven workflows using queues and asynchronous workers to connect model execution with existing Jira events, product services, and downstream enterprise applications.
• Created internal tooling that allowed engineering teams to register tools, configure prompts, compare LLM behavior, manage environment configuration, and rapidly prototype new AI-powered product workflows.
• Improved engineering delivery through Git, GitHub Actions, CI/CD pipelines, Docker builds, Kubernetes deployments, automated testing, code review, feature flags, and staged production releases.

Core: Python · JavaScript · TypeScript · React · Next.js · FastAPI · Node.js · LLMs · Prompt Engineering · Agentic AI · MCP · RAG · REST · GraphQL · PostgreSQL · Redis · OpenSearch · AWS · Docker · Kubernetes · Microservices · Git · CI/CD

Helped build Jasper from an early AI writing product into a scalable generative-AI platform, focusing on prompt engineering, LLM integrations, customer-facing AI workflows, and full-stack product development.

• Helped build Jasper's early AI writing product, enabling marketers to generate ads, emails, product descriptions, landing-page copy, social posts, and long-form content using OpenAI APIs, Python, JavaScript, TypeScript, React, and Node.js.
• Built the long-form AI editor experience, maintaining document context across multiple generations so users could continue, rewrite, expand, summarize, and transform existing content using React, TypeScript, backend APIs, prompt templates, and LLM context management.
• Developed Jasper's prompt-template platform, turning marketing use cases into reusable AI workflows using dynamic prompts, few-shot examples, tone controls, user variables, model parameters, and structured input templates.
• Helped evolve the product from simple one-shot generation into a flexible AI content editor by connecting frontend application state with prompt-processing services and model APIs using React, Next.js, TypeScript, Python, FastAPI/Node.js, and REST APIs.
• Built product functionality supporting brand-specific content generation, incorporating tone, writing style, company information, campaign context, and user preferences into dynamically generated model prompts.
• Developed multi-model abstraction services that allowed product features to interact with multiple LLM providers through common backend interfaces without tightly coupling application code to a single provider.
• Built conversational AI experiences that maintained user instructions and previous conversation context across interactions, supporting Jasper Chat-style content workflows.
• Developed prompt experimentation tooling for comparing temperature, top-p, token limits, model versions, system instructions, few-shot examples, latency, cost, and output quality before production rollout.
• Helped scale AI workloads through AWS services such as EC2, S3, Lambda, SQS, RDS, CloudWatch, Docker, Kubernetes, caching, asynchronous execution, and horizontally scalable application services.
• Worked closely with product and design from 0→1, rapidly prototyping new AI features and turning successful experiments into production features used by customers.

Core: Python · JavaScript · TypeScript · React · Next.js · FastAPI · Django · Node.js · OpenAI APIs · Prompt Engineering · Generative AI · PostgreSQL · Redis · AWS · Docker · Kubernetes · Microservices · Git · CI/CD

• Built backend features for enterprise cloud applications that automated data-heavy business workflows across multiple applications and internal services using Java, Python, REST APIs, SQL, and microservice architecture.
• Developed data-processing services for ingesting, validating, transforming, and serving large structured enterprise datasets using Python, Java, SQL, relational databases, batch processing, and asynchronous workers.
• Built internal data-management and operational tools that allowed enterprise teams to search records, inspect application state, and execute backend workflows through controlled application interfaces.
• Developed APIs connecting enterprise applications with databases, cloud services, and internal platforms using REST APIs, service-oriented architecture, JSON/XML integrations, authentication layers, and distributed services.

Core: Java · Python · JavaScript · SQL · REST APIs · Large Datasets · Microservices · Distributed Systems · OCI · Docker · Kubernetes · Relational Databases · Git · CI/CD · Enterprise Software

• Built backend services supporting high-volume consumer product workflows, processing user activity, content events, and product interactions through large-scale distributed systems using Python, JavaScript, backend APIs, and service-oriented architecture.
• Developed large-scale data pipelines that transformed, aggregated, and served behavioral and product datasets consumed by analytics, recommendation, ranking, and experimentation systems.
• Built APIs connecting React-based consumer product experiences with backend services, data platforms, and internal infrastructure running across distributed production environments.
• Developed internal engineering tools using JavaScript, React, Python, backend APIs, SQL-like query systems, and internal data platforms to help teams investigate product behavior and operational issues.

Core: Python · JavaScript · React · Backend APIs · Large Datasets · Data Pipelines · Distributed Systems · ML-Integrated Products · Microservices · Caching · Git · CI/CD · Enterprise Scale