Mid-Senior AI Python Engineer (Generative AI & Agentic Systems)

We are looking for a talented Mid-Senior AI Python Engineer to lead the design, development, and deployment of advanced Generative AI applications. This role involves moving beyond traditional large language model (LLM) wrapper applications to creating sophisticated, autonomous multi-agent pipelines and custom agent harnesses. The ideal candidate will combine strong software engineering skills with expertise in AI orchestration, particularly in building production-grade Python systems and designing complex Retrieval-Augmented Generation (RAG) frameworks and agent state machines.

Key Responsibilities:
- Architect, evaluate, and scale stateful multi-agent networks using tools like LangGraph and CrewAI to enable asynchronous parallel execution, memory management, and human-in-the-loop interventions.
- Design and optimize advanced RAG pipelines, incorporating semantic search, hybrid retrieval, dynamic routing, reranking, and intelligent metadata tagging to enhance system performance.
- Develop scalable agent execution environments that securely wrap LLMs with tool-calling protocols, sandboxing, and robust error handling and recovery mechanisms.
- Write clean, asynchronous, type-hinted, and modular Python code suitable for scalable production workloads, avoiding experimental or research-style scripting.
- Implement enterprise-grade AI observability by instrumenting telemetry tools such as LangSmith or Braintrust to monitor model latency, cost, prompt injection risks, and token usage while enforcing semantic guardrails.
- Collaborate closely with data engineers, product managers, and frontend developers to integrate complex backend agent logic into polished, user-facing applications.

Required Qualifications:
- 1 to 3 years of professional software engineering experience with expert-level Python skills, including deep understanding of async/await patterns, profiling, and both object-oriented and functional programming paradigms.
- 1 to 2 years of hands-on experience delivering production-grade Generative AI systems using APIs from providers like OpenAI, Anthropic, or open-weight models.
- Proven ability to build real-world applications using orchestration frameworks such as LangChain, LangGraph, and CrewAI, with a clear understanding of trade-offs between custom state graphs and high-level agent frameworks.
- Strong proficiency with vector databases (e.g., Pinecone, Weaviate, Qdrant, pgvector) and experience developing production pipelines for chunking and embedding data.
- Experience defining evaluation metrics for LLM applications to measure retrieval quality and reduce hallucinations.
- Familiarity with containerization (Docker) and deploying AI applications via CI/CD pipelines in cloud environments such as AWS, GCP, or Azure.

Preferred Qualifications:
- Experience working with Model Context Protocol (MCP) for standardized communication between agents and tools.
- Knowledge of LLM inference optimization engines like vLLM or Ollama.
- Contributions to open-source agentic frameworks or significant AI projects on GitHub.

This is a full-time position offering flexibility to work remotely or in a hybrid setting. The role presents an exciting opportunity to work at the forefront of AI engineering, shaping the next generation of intelligent, autonomous systems.