We're looking for a Senior AI Engineer to design, build, and ship production-grade LLM agents that reason over workforce and skills data on top of Loomra's semantic layer. You won't just prototype - you'll own agent workflows end to end, from design through evaluation, deployment into the tools employees use daily (Teams, Slack, Copilot), and iteration in front of enterprise customers. You'll work alongside product, data, and platform engineers to turn powerful capabilities into reliable, safe, and fast product experiences.
If you've built agents that actually made it to production - and you care as much about evaluation, guardrails, and reliability as you do about capability - we want to talk to you.
Responsibilities
Design and build multi-agent systems and orchestration - intent routing, planning, tool use, and coordination across specialized agents.
Implement retrieval and RAG pipelines over structured and unstructured workforce data, grounded in our knowledge graph connecting people, jobs, and skills.
Integrate LLMs with tool/function calling and protocols such as MCP to give agents controlled access to HCM systems, business logic, and workflows.
Build evaluation harnesses, guardrails, and safety/bias checks, and work within the governance engine so agents behave reliably, respect customer policies, and produce a full audit trail.
Ship agents in a model-agnostic way across providers (Anthropic, Google, IBM watsonx) and deploy them into Teams, Slack, and Copilot.
Optimize agents for latency, cost, and reliability at enterprise scale.
Take agents from prototype to production - with monitoring, observability, and a fast iteration loop.
Partner closely with product, data, and platform teams to translate customer needs into agent capabilities.
Requirements: 5+ years building production software
Proven experience building and shipping LLM agents to production - not just demos or prototypes.
Hands-on with at least one agent orchestration framework (e.g. LangGraph, LangChain, AutoGen, CrewAI, Semantic Kernel, or similar).
Strong Python and solid software engineering fundamentals.
Prompt engineering paired with systematic, measurable evaluation of LLM outputs.
Experience with tool use / function calling and integrating LLMs with external systems.
Track record deploying, monitoring, and maintaining AI in production (cloud, CI/CD, observability).
Nice to Have
2+ years hands-on with LLMs / generative AI.
Practical experience with RAG, embeddings, and vector databases (e.g. pgvector, Pinecone, or similar)
Experience with MCP, agent memory, and planning/reasoning patterns.
Background in HR tech, people data, or skills ontologies.
Knowledge graph / graph ML experience (knowledge graphs, GNNs).
Responsible AI: bias evaluation, guardrails, and AI governance.
Experience working across multiple model providers (e.g. Anthropic, Google, IBM watsonx) rather than a single vendor.
This position is open to all candidates.