Senior Python AI Engineer
Summary
Build and optimize a high-load financial LLM system using Python, LangGraph, FastAPI, and Elasticsearch to power Ask Seeking Alpha.
Role Description
We are developing Ask Seeking Alpha — a high-load financial analysis system based on Large Language Models. The architecture is built on complex multi-agent orchestration using LangGraph, FastAPI, and Elasticsearch.
We are looking for a Senior Python AI Engineer specialized in Generative AI to:
- Design agent workflows
- Optimize interactions with models (OpenAI, AWS Bedrock)
- Ensure the reliability of non-deterministic systems in production
Tech Stack:
- Python (Asyncio)
- FastAPI
- LangChain
- LangGraph
- Pydantic
- Elasticsearch
- AWS Bedrock / OpenAI API
- LangSmith
Qualifications
- Strong proficiency in modern Python
- Deep understanding of asynchronous programming (asyncio) patterns
- Experience with FastAPI and Pydantic (v2)
- Production experience with LangChain
- Hands-on experience or deep conceptual understanding of LangGraph (or similar state-machine based agent frameworks)
- Strategies for handling LLM hallucinations and ensuring reliable outputs
- Experience forcing LLMs to adhere to strict schemas (Pydantic/JSON mode)
- Advanced strategies for managing limited context windows
- Understanding the trade-offs between model size, latency, and cost
Requirements
- Reduce end-to-end latency through asynchronous processing and streaming (SSE)
- Implement semantic caching strategies to minimize API costs and response time
- Optimize token usage without sacrificing answer quality
- Implement automated evaluation pipelines using LangSmith
- Set up regression testing for prompts and agents to measure quality (correctness, faithfulness) before deployment
- Refine retrieval strategies
- Work on hybrid search implementation (Keyword + Vector), re-ranking, and query expansion
Nice to Have
- Experience with Elasticsearch (DSL queries, analyzers)
- Knowledge of vector databases and embedding models
- Background in FinTech or familiarity with financial data structures