Collaborate closely with engineering, operations, and business stakeholders to understand workflows, identify pain points, and design AI-driven solutions with measurable impact.
Translate complex requirements into scalable AI-enabled services and technical concepts.
Contribute directly to the design and architecture of systems powered by LLMs and retrieval technologies.
Build AI Systems for Production
Develop and maintain scalable, production-grade AI services focused on: LLMs RAG pipelines Hybrid retrieval Semantic search Vector search Agentic workflows
Build backend APIs, data pipelines, and integrations while ensuring reliability, observability, and engineering best practices.
Own the full development lifecycle: architecture, implementation, testing, deployment, and monitoring.
AI Evaluation, Prompt Engineering & Data Quality
Design rigorous evaluation strategies for AI output quality, retrieval accuracy, and model behavior.
Treat prompt engineering as an engineering and experimentation discipline.
Ensure high standards for data quality and contextual grounding across AI systems.
Mentor junior team members on AI engineering, experimentation, and evaluation practices.

5+ years of experience in Software Engineering, with strong exposure to AI, NLP, or Information Retrieval.
Proven experience building and operating AI solutions in production and enterprise environments.
Ability to bridge experimental Data Science workflows with reliable and maintainable software engineering practices.
Strong proficiency in modern Python (3.11+), including: async/await typing Pydantic
Experience with: Docker CI/CD testing frameworks (pytest) code quality tooling (ruff, mypy) Git workflows and code reviews
Hands-on experience with: LLMs Prompt Engineering RAG GraphRAG Vector databases / OpenSearch AI evaluation pipelines
Nice to Have: Experience with AWS Bedrock or Azure OpenAI. Familiarity with MCP (Model Context Protocol) and modern AI interface standards.

Senior AI Backend Engineer

Key skills