Senior AI Engineer

Key Responsibilities

• Design, build, and scale production-grade AI systems powered by Large Language Models.
• Build reliable AI pipelines including retrieval, tool calling, structured outputs, context management, and evaluation frameworks.
• Own AI features end-to-end, from architecture through deployment, monitoring, and continuous improvement.
• Design systems that are scalable, observable, reliable, and maintainable.
• Debug production issues and continuously improve latency, reliability, and model performance.
• Build internal tooling to improve AI quality, experimentation, and developer productivity.
• Work closely with product and engineering teams to solve customer problems using AI where appropriate, and avoid AI where simpler solutions are better.
• Evaluate new models, frameworks, and research papers, and translate them into production-ready systems.
• Mentor engineers through code reviews, architecture discussions, and engineering best practices.

Experience

• 7+ years of software engineering experience building and shipping production systems.
• Hands-on experience building and deploying LLM or ML-powered applications in production environments.
• Experience working in fast-paced startup environments with end-to-end ownership.

Technical Skills

• Strong programming skills in Python and modern software engineering practices.
• Deep understanding of LLM application development and LLMOps.
• Strong understanding of distributed systems, APIs, asynchronous processing, and scalable backend architectures.
• Experience working on cloud platforms. AWS is preferred, while GCP or Azure experience is also acceptable.
• Familiarity with containers, CI/CD pipelines, model deployment, monitoring, and production observability.
• Strong debugging skills with experience troubleshooting production systems.
• Comfortable using AI-assisted development tools while maintaining high engineering standards and code quality.

What We're Looking For

You're a great fit if you:

• Have spent the last several years shipping production software, not prototypes or notebooks.
• Understand the difference between writing code and building durable engineering systems.
• Can independently own difficult engineering problems from idea to production.
• Make thoughtful engineering decisions instead of blindly applying AI or frameworks.
• Build clean interfaces, write maintainable code, and believe in disciplined reviews and testing.
• Can quickly identify problems in AI-generated code and improve upon it.
• Enjoy reading research papers, experimenting with new ideas, and validating them through production engineering.
• Thrive in ambiguity and enjoy building systems where no reference implementation exists.

Success in This Role

You'll be successful if you:

• Build reliable AI systems that customers depend on every day.
• Take ownership of complex engineering problems and drive them to completion.
• Improve the scalability, latency, and quality of our AI platform.
• Continuously raise the engineering bar through thoughtful design, testing, and code quality.
• Help shape the future architecture of RevRag AI's production AI infrastructure.

Bonus Points

Experience with any of the following will be highly valued:

• Production Voice AI systems
• LiveKit Agents
• Pipecat
• WebRTC
• Telephony integrations
• Fine-tuning using LoRA or QLoRA
• Model inference optimization and serving
• Indian language NLP, code-switching, and multilingual evaluation
• AI systems for regulated industries such as BFSI or Healthcare
• Building production AI platforms from the ground up