Mandatory Requirements
• 5+ years of software development experience.
• At least 1 year of hands-on experience building production agentic systems, AI agents, or LLM-powered workflows.
• Strong experience with Python, including backend development and production services.
• Full-stack proficiency with React and Python, ideally 3+ years.
• Experience building RAG systems, including embeddings, vector databases, retrieval pipelines, reranking, and grounding techniques.
• Hands-on experience with LangGraph.
• 1+ years of experience working in an AWS environment.
• Strong understanding of LLM tool calling, agent state management, workflow orchestration, and multi-step reasoning.
• Experience integrating with APIs, databases, and data processing systems.
• Strong SQL skills and comfort working with structured business data.
• Experience deploying, monitoring, and debugging production systems.
Strong Advantages
• Experience with LangChain, LlamaIndex, OpenAI API, Anthropic Claude, Bedrock, or similar LLM platforms.
• Experience with FastAPI, Celery, Temporal, Airflow, Step Functions, or other workflow orchestration frameworks.
• Experience with vector databases such as Pinecone, Weaviate, Qdrant, pgvector, OpenSearch, or similar.
• Experience with data warehouses such as Snowflake, BigQuery, Redshift, or Databricks.
• Experience building AI evaluation frameworks, automated test sets, golden datasets, or agent regression tests.
• Experience with observability tools such as LangSmith, OpenTelemetry, Datadog, CloudWatch, or similar.
• Familiarity with semantic layers, ontologies, knowledge graphs, metric stores, or business logic modeling.
• Experience with secure AI systems, including prompt-injection mitigation, access control, audit logs, and sensitive-data handling.
• Background in marketing analytics, BI, decision intelligence, or enterprise SaaS.
What You Bring
• You care about building AI systems that are reliable, explainable, and production-ready.
• You understand that great AI products require more than prompting: they require architecture, data grounding, evaluation, governance, and strong engineering.
• You are comfortable working in an early-stage startup environment where requirements evolve quickly and execution matters.
• You can collaborate closely with product, data, and domain experts to turn ambiguous business problems into working AI systems.