DevSavant is seeking a senior, self-directed GenAI Full-Stack Engineer who thrives at the intersection of rapid innovation and production excellence.
The role involves owning the complete lifecycle of GenAI initiatives, including prototyping, pressure-testing, iterating, and productionizing successful proof-of-concepts.
Responsibilities include architecting and developing LLM-powered workflows, designing production RAG systems, building multi-agent orchestration, creating real-time AI interfaces, connecting GenAI pipelines to enterprise data, implementing formal prompt lifecycles, adding runtime guardrails, and optimizing for cost and latency.
The engineer will also design scalable architectures, implement comprehensive testing, build CI/CD pipelines, deploy with container orchestration, and monitor AI-specific metrics.
Requirements:
Candidates must have 5+ years of professional full-stack development experience.
A minimum of 2 years of experience shipping GenAI/LLM features to production is required.
Candidates should have at least 1 year of experience with vector databases and production RAG systems.
A proven track record of 0→1 product development and experience with high-traffic applications (10K+ concurrent users) is essential.
The ideal candidate should be autonomous, accountable, have a bias for action, a comprehensive testing mindset, a continuous learning attitude, and strong communication skills.
Benefits:
The position offers a remote-first work environment, allowing for flexibility in work location.
Employees will have the opportunity to work with cutting-edge GenAI tooling and innovative projects.
The role encourages rapid prototyping and innovation, providing a dynamic and engaging work experience.
Team members will be part of a unique approach that focuses on maturing successful prototypes into robust production services.