Architect complex, multi-agent workflows using Microsoft AI tech stack.
Design, develop and deploy agents to handle loops, interruptions, and human-in-the-loop interventions.
Build reliable "tool layers" that allow LLMs to safely interact with internal APIs, databases, and third-party SaaS platforms.
Design persistence layers to manage agent memory, conversational history, and context windows efficiently.
Build production-grade data retrieval and integration systems. Optimize vector indexing, document chunking, and re-ranking algorithms to ensure high-precision context retrieval.
Collaborate with Data Engineers to curate "Golden Datasets" for agent consumption.
Build CI/CD pipelines for AI that include "LLM-as-a-Judge" testing.
Instrument applications with tracing tools to visualize agent reasoning chains, monitor latency, and debug failures in production.
Monitor token usage and latency, optimizing prompt density and caching strategies to maintain high performance at sustainable costs.
Rapidly validate new ideas using state-of-the-art models, then refactor successful prototypes into maintainable, tested production code.
Requirements:
Bachelor’s degree and 5 years of software engineering experience, with exposure to AI/ML applications OR 9 years of software engineering experience, with exposure to AI/ML applications.
2+ years specifically building with LLMs, with deep familiarity in: Orchestration: LangChain, LangGraph, or similar state-based frameworks.
Vector DBs: Pinecone, Weaviate, or pgvector.
Prompt Engineering: Advanced techniques (Chain-of-Thought, ReAct, Few-Shot).
Experience not just building demos, but operating them. You know how to handle rate limits, context window overflows, and non-deterministic errors.
Ability to explain "probabilistic software" to non-technical stakeholders—managing expectations that agents are never 100% accurate, but can be 100% useful.
Excellent communication skills, with experience in documenting technical designs, sharing insights, and enabling team knowledge transfer.
Benefits:
Opportunity to design and build the next generation of enterprise AI agents.
A collaborative environment where experimentation and innovation are encouraged.