Senior Python AI Engineer – LLM, Multi-Agent Systems

This is a fully remote position, open to applicants in Ukraine.

📋 Description

• Develop and execute intricate agent orchestration logic utilizing LangGraph

• Establish state management, conditional routing, and error handling within the agent graph

• Create and enhance the tool layer/function calling for LLM engagement with internal financial APIs and databases

• Decrease end-to-end latency through asynchronous processing and streaming (SSE)

• Apply semantic caching techniques to reduce API expenses and response times

• Optimize token utilization while maintaining answer quality

• Develop automated evaluation pipelines using LangSmith

• Establish regression testing for prompts and agents to assess correctness and faithfulness prior to deployment

• Improve retrieval methods, including hybrid keyword and vector search, re-ranking, and query expansion

⛳️ Requirements

• Strong expertise in contemporary Python

• Profound knowledge of asynchronous programming (asyncio) patterns

• Experience with FastAPI and Pydantic v2

• Practical experience with LangChain

• Hands-on experience or significant theoretical understanding of LangGraph or comparable state-machine based agent frameworks

• Techniques for managing LLM hallucinations and ensuring dependable outputs

• Experience enforcing LLMs to comply with strict schemas using Pydantic/JSON mode

• Advanced strategies for context-window management

• Awareness of trade-offs between model size, latency, and cost

• Familiarity with Elasticsearch, DSL queries, and analyzers (a plus)

• Knowledge of vector databases and embedding models (a plus)

• Background in FinTech or familiarity with financial data structures (a plus)

🏝️ Benefits

• Flexible, balanced work environment with remote work options

• Continuous learning and career progression opportunities

• Benefits that support personal well-being and professional aspirations