• Design and implement end-to-end AI system architectures. • Develop backend services, APIs, and data pipelines integrating AI models. • Write and maintain Python code leveraging Azure cloud services. • Prepare, structure, and validate training datasets with production constraints. • Contribute to technical discussions and architectural decisions.

• Design and develop AI-powered solutions using Microsoft Azure services, including OpenAI, Cognitive Search, Vision, Document Intelligence, and Cosmos DB for vector storage. • Build and iterate on retrieval-augmented generation (RAG) pipelines and knowledge-grounded architectures, including GraphRAG and emerging techniques like OmniRAG. • Rapidly prototype AI applications tailored to specific client needs, such as document digitization, data vectorization, and content generation workflows. • Contribute to the architecture and implementation of advanced AI systems, including agent-based orchestration and integration with modern APIs and platforms. • Prepare and structure training data, including labeled inputs for both text and image-based models, with a focus on production readiness and model performance. • Evaluate and adopt new tools and frameworks based on AI/ML advancements, ensuring that implementations are stable and scalable. • Collaborate across teams to deliver high-impact, cloud-native applications using Python (especially Azure's AI SDK). Exposure to JavaScript/TypeScript or Node.js is considered an asset. • Apply familiarity with engineering documentation and visuals (e.g., diagrams, schematics) to enhance AI-driven workflows where applicable.

• Define precise technical requirements for scalable agent architecture, including necessary reasoning frameworks, risk management systems, and knowledge retrieval interfaces required for complex decision-making. • Serve as the hands-on technical lead capable of building, testing, and deploying both interim (e.g., RAG-based systems) and highly complex agentic AI solutions. • Work alongside strategy leads to ensure that the technical prerequisites for achieving fully autonomous agentic operations are met on the twelve-month roadmap. • Oversee the technical integration and scaling of deployed AI agents within specific operational workflows (e.g., automating specific GTM tasks). • Ensure seamless deployment with rigorous validation testing, monitoring agent performance, and iterating on technical builds to improve decision accuracy and reduce latency.

WHAT WE DO Founded in 2007, Growth Acceleration Partners (GAP) is a consulting and technology services company. We consult, design, build and modernize revenue-generating software and data engineering solutions for clients. With modernization services and AI tools, we help businesses achieve a competitive advantage through technology. GAP’s remote, integrated engineering teams use end-to-end solutions to innovate and align with your business goals. We have 600+ English-speaking engineers based in Latin America and approximately 20 U.S.-based engineers. With some of the highest customer satisfaction scores in the industry, GAP’s focus is customer and employee success. GAP is a woman-owned company headquartered in Austin Texas. We are a values-based company focused on growing our people by investing in education, onsite English classes and training in the latest technologies, including AI, data analytics and machine learning. Our goal is to provide solutions for our customers that help them achieve critical business outcomes, while enabling our GAPSters and our communities to attain long-term success. Summary We are looking for a Staff AI Python Software Engineer to lead the design and implementation of AI-powered backend systems within a fast-growing, product-driven environment. This is a high-impact, product-focused role where you will take ownership from problem definition to delivery. You will operate with a high level of autonomy, translating product needs into scalable technical solutions and driving execution across the development lifecycle. This role requires a strong combination of Staff-level Python engineering expertise and deep experience working within product teams. You should be comfortable owning a full feature or epic end-to-end — from defining the implementation approach to breaking down tasks, estimating effort, and delivering the solution. Additionally, this is an AI-native engineering role. You are expected to have advanced, hands-on experience using AI assistants, coding agents, and automation workflows, not only as support tools but as multipliers of your productivity. You should be comfortable delegating work to AI systems, orchestrating workflows, and accelerating delivery through these tools. Professional Experience •6+ years of experience in software engineering with strong Python expertise •Proven experience working in product-driven environments •Experience owning end-to-end delivery of features or epics •Strong experience in system design and scalable architectures •Advanced hands-on experience using AI tools, coding agents, or AI-assisted development workflows Key Responsibilities •Own the design and delivery of backend systems and AI-powered features from concept to production •Translate product requirements into scalable architecture and implementation strategies •Break down features or epics into tasks, estimates, and delivery plans •Manage and own the full development lifecycle, including prioritization and release flow •Build and integrate systems leveraging LLMs, NLP, and voice technologies (STT/TTS) •Use AI tools and agents to accelerate development, debugging, and decision-making •Delegate and orchestrate work across AI-assisted workflows and automation tools •Collaborate closely with product, design, and engineering teams to drive outcomes •Mentor engineers and influence technical direction and best practices Technical Skills Strong experience in several of the following areas: •Backend & Architecture: Python, scalable system design, distributed systems •Product Engineering: Experience working closely with product teams, owning features end-to-end •AI-Native Development: Advanced use of AI assistants, coding agents, and automation workflows •AI & LLMs: Experience integrating LLM APIs, NLP systems, or AI-driven features •Cloud & DevOps: AWS, GCP, or Azure, Docker, CI/CD pipelines •APIs & Data: REST APIs, data processing, databases •Voice Systems (Plus): STT/TTS integrations or conversational systems Nice to Have •Experience with RAG architectures or AI agent frameworks •Experience building AI-first or voice-enabled products •Exposure to real-time systems or conversational interfaces Soft Skills •Advanced English proficiency •Strong product mindset and business understanding •High ownership and autonomy •Ability to move fast and deliver iterative solutions •Strong decision-making and prioritization skills •Mentorship and leadership capabilities At Growth Acceleration Partners, we're an equal opportunity employer committed to building a diverse and inclusive team. We value everyone's unique background, and we provide equal opportunities regardless of race, color, creed, religion, sexual orientation, gender identity, age, national origin, disability, marital status, veteran status or any other personal right protected by law. We foster a culture of belonging and strive to provide a welcoming environment where everyone feels safe to contribute and grow.