2 months ago

Senior Python AI Engineer (LLM & Multi-Agent Systems)

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 21 hours agoStatus: Live

Job Summary

Build and scale “Ask Seeking Alpha,” a high-load financial analysis system powered by Large Language Models and multi-agent orchestration. Design agent workflows with LangGraph, engineer tool/function calling for internal financial APIs, and improve reliability for non-deterministic outputs. Optimize performance with async streaming, caching, and token efficiency, while implementing evaluation and regression testing with LangSmith. Advance RAG using hybrid search, re-ranking, and query expansion.

Location: Warsaw

Workplace: Remote

Employment Type: Full time

Job Function: Data Science & Machine Learning

Seniority: Mid level

Key Responsibilities

•Design and implement complex agent orchestration logic using LangGraph, including state management, conditional routing, and error handling.
•Build and optimize the tool layer (function calling) so LLMs can interact accurately with internal financial APIs and databases.
•Reduce end-to-end latency using asynchronous processing and streaming (SSE).
•Implement semantic caching to minimize API costs and response time, and optimize token usage without reducing answer quality.
•Set up observability and automated evaluation pipelines with LangSmith, including regression testing for prompts and agents; improve RAG with hybrid search, re-ranking, and query expansion.

Key Requirements

•Strong modern Python with mandatory asynchronous programming (asyncio) and experience with FastAPI and Pydantic (v2).
•Production experience with LangChain and hands-on or deep conceptual understanding of LangGraph (or similar state-machine agent frameworks).
•Strategies to manage LLM non-determinism, including handling hallucinations and ensuring reliable outputs (e.g., self-correction loops, CoT/ReAct).
•Experience enforcing structured outputs via strict schemas (Pydantic/JSON mode) for reliable downstream processing.
•Advanced context optimization for limited context windows (e.g., summarization chains, sliding windows, selective context injection), plus understanding inference cost/latency trade-offs.

Experience:FinTech

Skills:Problem-solvingReliability focusAttention to detail

Tech Stack:PythonAsyncioFastAPILangChainLangGraphPydanticElasticsearchAWS BedrockOpenAI APILangSmithSSEJSON mode

Company Brief

Seeking Alpha

Provides financial news, market analysis, and investment research for retail investors and professionals. The platform features articles, earnings coverage, stock ideas, portfolio tools, and community discussions focused on public markets.

Industry: News, Journalism & Broadcasting

Company Size: Large (251 to 1,000 employees)

Growth: Established Company

Headquarters: New York City, United States

Founded: 2004

Website LinkedIn

Loading job details...

Preparing the role view and application actions.

Seeking Alpha

2 months ago

Senior Python AI Engineer (LLM & Multi-Agent Systems)

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 21 hours agoStatus: Live

Job Summary

Location: Warsaw

Workplace: Remote

Employment Type: Full time

Job Function: Data Science & Machine Learning

Seniority: Mid level

Key Responsibilities

•Design and implement complex agent orchestration logic using LangGraph, including state management, conditional routing, and error handling.
•Build and optimize the tool layer (function calling) so LLMs can interact accurately with internal financial APIs and databases.
•Reduce end-to-end latency using asynchronous processing and streaming (SSE).
•Implement semantic caching to minimize API costs and response time, and optimize token usage without reducing answer quality.
•Set up observability and automated evaluation pipelines with LangSmith, including regression testing for prompts and agents; improve RAG with hybrid search, re-ranking, and query expansion.

Key Requirements

•Strong modern Python with mandatory asynchronous programming (asyncio) and experience with FastAPI and Pydantic (v2).
•Production experience with LangChain and hands-on or deep conceptual understanding of LangGraph (or similar state-machine agent frameworks).
•Strategies to manage LLM non-determinism, including handling hallucinations and ensuring reliable outputs (e.g., self-correction loops, CoT/ReAct).
•Experience enforcing structured outputs via strict schemas (Pydantic/JSON mode) for reliable downstream processing.
•Advanced context optimization for limited context windows (e.g., summarization chains, sliding windows, selective context injection), plus understanding inference cost/latency trade-offs.

Experience:FinTech

Skills:Problem-solvingReliability focusAttention to detail

Tech Stack:PythonAsyncioFastAPILangChainLangGraphPydanticElasticsearchAWS BedrockOpenAI APILangSmithSSEJSON mode

Company Brief

Seeking Alpha

Industry: News, Journalism & Broadcasting

Company Size: Large (251 to 1,000 employees)

Growth: Established Company

Headquarters: New York City, United States

Founded: 2004

Website LinkedIn