Required Qualifications
● 3+ years of Software Engineering experience, with a background in Python and FastAPI (or similar).
● 1+ year of experience specifically focused on LLM-based Agents in a production environment.
● Deep Expertise in Agentic Patterns: Proven experience implementing ReAct, Plan-and-Execute, or Multi-Agent Supervisor architectures.
● Production Infrastructure: Hands-on experience with modern Vector Databases and Search Engines (e.g., Pinecone, Milvus, Weaviate, Qdrant, Chroma, or pgvector) and semantic caching strategies.
● Robustness Mindset: A track record of handling non-deterministic failures (e.g., implementing custom retry logic and fallback strategies for failed tool calls).
Preferred Qualifications (The "Plus" Factors)
● Experience with Fine-tuning smaller models (e.g., Llama 3) for specific tool-calling tasks to reduce latency.
● Knowledge of Data Privacy (handling PII in agent prompts) and AI Security best practices.
● Prior experience building agents for specialized sectors like Fintech or Supply Chain.