Senior Support Engineer (Full Stack Developer - AI/LLM Infrastructure)

If you haven't built and maintained AI/LLM systems in production, developed full-stack applications with complex backend architectures, or debugged distributed systems under pressure, we kindly ask that you don't apply. We need a hands-on developer with strong support engineering experience who codes daily while ensuring system reliability.

About Us

We're an AI-first startup revolutionizing speech-to-text technology through cutting-edge LLM integration and machine learning pipelines. Our platform combines advanced AI models with real-time processing capabilities, serving enterprise clients who demand both accuracy and reliability. As we scale our AI infrastructure globally, we need a technical leader who can both build and support our systems.

Role Overview

We're seeking a Senior Support Engineer who is primarily a hands-on full-stack developer with deep AI/LLM infrastructure experience and production support expertise. This isn't a traditional support role - you'll spend 70% of your time coding and building systems, 30% on support and reliability engineering.

You'll architect and implement AI/LLM integrations, develop full-stack applications, optimize backend performance, and maintain production systems. This role requires someone who can write production code, debug complex distributed systems, and take ownership of both development and operational excellence.

Key Responsibilities

1. AI/LLM Infrastructure Development

- Design and implement LLM integration pipelines (OpenAI, Anthropic, local models)

- Build AI model inference systems with real-time processing capabilities

- Develop prompt engineering frameworks and model optimization systems

- Create AI/ML monitoring and evaluation frameworks

- Implement vector databases and semantic search capabilities

- Build automated model training and deployment pipelines

2. Full Stack Development - Backend Focus

- Develop scalable backend APIs using Python/Node.js/Go

- Design and optimize database architectures (PostgreSQL, MongoDB, Redis)

- Build microservices architectures with proper service communication

- Implement authentication, authorization, and security frameworks

- Create data processing pipelines for audio/text transcription workflows

- Develop real-time WebSocket and event-driven systems

3. Production Support & System Reliability

- Monitor and maintain production AI/LLM systems with 99.9% uptime

- Respond to critical incidents and perform root cause analysis

- Debug complex distributed system issues across the full stack

- Implement comprehensive monitoring, alerting, and observability systems

- Maintain CI/CD pipelines and automated deployment processes

- Create technical documentation and incident response procedures

Technical Requirements

1. AI/LLM Infrastructure Experience

- 3+ years hands-on experience with LLM APIs (OpenAI, Anthropic, Hugging Face)

- Production experience with AI model deployment and inference systems

- Knowledge of vector databases (Pinecone, Weaviate, Chroma) and embeddings

- Experience with ML frameworks (PyTorch, TensorFlow, Transformers)

- Understanding of prompt engineering, RAG systems, and AI evaluation metrics

2. Backend Development Expertise

- 5+ years full-stack development with strong backend focus

- Expert-level Python, Node.js, or Go for backend services

- Advanced database optimization (PostgreSQL, MongoDB, Redis)

- Microservices architecture and API design patterns

- Experience with message queues (RabbitMQ, Apache Kafka)

- Cloud infrastructure expertise (AWS, GCP, Azure)

3. Production Support Experience

- 3+ years maintaining production systems under high load

- Incident response and on-call rotation experience

- Proficiency with monitoring tools (Datadog, New Relic, Grafana)

- Experience with containerization (Docker, Kubernetes)

- Knowledge of CI/CD pipelines and Infrastructure as Code

4. Full Stack Capabilities

- Frontend development with React, Vue.js, or Angular

- Understanding of modern web technologies and performance optimization

- Experience with real-time applications and WebSocket implementation

- Mobile development experience (React Native, Flutter) preferred

Preferred Qualifications

- Experience with speech-to-text, NLP, or audio processing systems

- Background in fintech, healthcare, or regulated industries

- Contributions to open-source AI/ML projects

- Experience with startup environments and rapid scaling

- DevOps and infrastructure automation experience

What You'll Build

- AI-powered transcription services with multi-model inference

- Real-time audio processing pipelines with LLM integration

- Scalable backend APIs serving millions of requests

- Monitoring dashboards for AI model performance and system health

- Automated deployment systems for AI/ML models

- Full-stack applications for enterprise clients

Technical Environment

- AI/ML Stack: OpenAI GPT-4, Anthropic Claude, Hugging Face models, PyTorch

- Backend: Python/FastAPI, Node.js, PostgreSQL, Redis, Docker, Kubernetes

- Cloud: AWS (Lambda, ECS, RDS, S3), infrastructure automation with Terraform

- Monitoring: Datadog, Grafana, ELK stack, custom AI model monitoring

- Frontend: React, TypeScript, modern web frameworks

Working Arrangements

- 100% remote, full-time position with rotating shift schedule for global engineering support coverage

- Engineering support coverage across multiple time zones (building toward 24/7 coverage as the team grows)

- Collaborative environment with structured handoffs between regional support teams

- Reasonable on-call responsibilities with fair rotation

- Modern collaboration tools, comprehensive documentation systems, and remote-first culture

What We Offer

- Competitive compensation package

- Opportunity to work with cutting-edge AI technology and solve complex technical challenges at scale

- Supportive team culture despite global support requirements

- Clear career growth path toward senior technical leadership, specialized expertise, and architectural roles

How to Apply

Submit your resume with a cover letter addressing:

- Your hands-on experience building AI/LLM systems in production

- Specific examples of full-stack applications you've developed

- Your approach to maintaining production systems under pressure

- Experience with both development and support engineering responsibilities

- Examples of complex backend optimization or distributed system debugging

Include GitHub profile or portfolio demonstrating:

- AI/ML projects with real-world applications

- Full-stack development capabilities

- Production system monitoring and reliability engineering

We're looking for a technical leader who can build our AI infrastructure while ensuring operational excellence. If you're passionate about both creating and maintaining cutting-edge AI systems, we'd love to hear from you.