Q
Senior AI Engineer
Not specifiedFull-timeAI EngineeringIT Services
Design, build, and scale production AI and generative AI solutions for complex enterprise environments, combining software engineering, cloud infrastructure, and system architecture.
Responsibilities
- Design and develop end-to-end AI and generative AI systems from prototype through production, using LLMs and agent frameworks such as LangGraph.
- Build scalable backend services, data and inference pipelines, RAG and embedding architectures, and highly available cloud-native systems.
- Design distributed microservices and event-driven architectures for scale and reliability.
- Implement observability and AI software development lifecycle practices.
- Integrate security, governance, and compliance capabilities into AI solutions.
Requirements
- At least 8 years of production software development experience.
- At least 5 years of hands-on Python and JavaScript or TypeScript experience, including concurrency, asyncio, and Pydantic.
- At least 3 years of hands-on AWS and cloud-native architecture experience, including Docker, Kubernetes, S3, Lambda, CI/CD, observability, and managed messaging or streaming platforms.
- At least 4 years designing scalable microservices, event-driven architectures, and distributed backend systems, including high-load and failure scenarios.
- Strong knowledge of software engineering, distributed systems, scalability, reliability, and production-grade development.
- Strong problem-solving and technical communication skills, and ability to work with multidisciplinary teams.
Nice to have
- Experience deploying production LLM solutions and managing non-deterministic AI outputs at scale.
- Experience with AI evaluation and monitoring, including LLM-as-a-Judge.
- Familiarity with MCP, A2A protocols, and agentic architectures.
- Experience designing REST or GraphQL APIs and knowledge of OAuth 2.0, JWT, or OIDC.