You are a Senior AI Software Engineer looking to join a GenAI Infrastructure team and build production-grade GenAI capabilities and the infrastructure behind them. You will be a hands-on engineer focused on AI agents, RAG pipelines, tool-calling workflows, backend services, data access layers, evaluation, observability, and reusable GenAI infrastructure used across product teams. You will not be focused solely on model research or prompt design. Instead, you will be a strong software engineer who can design, build, ship, and operate reliable AI-powered systems in production.
A Day In Your Life
Build reusable infrastructure, SDKs, and internal frameworks for AI-powered product capabilities.
Design and implement AI agents, RAG flows, tool-calling workflows, and LLM orchestration pipelines.
Build production-grade GenAI services, APIs, and backend infrastructure.
Integrate LLM workflows with internal microservices, data platforms, vector search, and event-driven systems.
Design secure data-access patterns that enforce authorization, tenant separation, and user-level scope.
Implement evaluation, tracing, monitoring, and quality-control mechanisms for GenAI systems.
Improve latency, reliability, fallback behavior, cost efficiency, and production readiness.
Work on customer-facing AI experiences, including conversational and proactive agentic product flows.
Collaborate with backend engineers, product managers, data engineers, AI/ML engineers, and domain experts.
Requirements: 6+ years of professional software engineering experience.
Strong Python development skills.
Strong backend engineering background, including APIs, services, integrations, or microservices.
Proven experience designing, shipping, or operating LLM-powered applications or GenAI systems.
Experience with RAG, AI agents, tool/function calling, prompt orchestration, evaluation, and observability.
Experience with microservices, distributed systems, and production backend architecture.
Strong understanding of system design, reliability, security, scalability, latency, and maintainability.
Ability to work with complex data models and expose them safely through AI systems.
Ability to operate in ambiguous technical areas and turn prototypes into production-ready systems.
Strong communication skills and ability to explain technical decisions clearly.
Preferred Qualifications:
Experience with LangChain, LangGraph, or LangSmith.
Experience with Go, MongoDB, Databricks, Kubernetes, Docker, REST APIs, vector search, or event-driven systems.
Experience with Azure OpenAI, Gemini, or similar LLM platforms.
Experience building or using knowledge graphs, GraphRAG, or graph databases such as Neo4j.
Experience building multi-agent systems or orchestrating multiple specialized agents/tools in production.
Experience building internal platforms, SDKs, developer tools, or shared engineering infrastructure.
Experience with authorization, data segregation, multi-tenant systems, or user-level data scoping.
Experience in industrial, IoT, predictive maintenance, manufacturing, or operational-data domains.
This position is open to all candidates.