Merciv
Posted 73 days agoVerified live 1d ago
Rengo AI - AI Engineer
Brief overview
Remote
3+ yrsMinimum
PythonLLM applicationsRAG systemsStructured generationFunction callingAgent workflowsTime-series dataEvent-driven pipelinesAnalytics systemsPostgresVector databasesStream processing pipelinesBatch processing pipelinesCloud infrastructureOpenAI APIAnthropic APIObservability systems
About the company
Mercivmerciv.com
Merciv is a technology company that combines AI and human insight to help businesses observe and act upon relevant signals in their data.
Job description
Summary
Merciv is building the intelligence layer for fund management with Rengo AI, focusing on next-generation portfolio monitoring systems for investment teams. As a Founding AI Engineer, you will develop core systems that provide AI-driven insights and monitoring for institutional investors.
Responsibilities
- Ingest portfolio + market + position-level data
- Detect meaningful changes and anomalies
- Generate structured investment insights
- Explain performance and risk drivers in natural language + structured outputs
- Build real-time and batch systems that monitor: portfolio performance (PnL, attribution, drawdowns), exposure shifts (sector, geography, asset class), risk signals (volatility, correlation, concentration), position-level changes
- Build systems that detect: significant portfolio movements, abnormal price/volume behavior in holdings, drift from target allocations, risk regime changes
- Generate structured outputs such as: daily / weekly portfolio reports, performance explanations (“why did we lose/gain?”), exposure breakdowns, risk commentary
- Integrate: positions & holdings data, market data feeds, internal fund metadata, external news & filings (optional enrichment layer)
- Design LLM pipelines that: avoid hallucinated financial reasoning, produce structured, verifiable outputs, ground insights in actual portfolio data
- Build evaluation frameworks for correctness of financial narratives
Skills
- 3–7+ years in backend, data engineering, or ML systems
- Strong Python (mandatory)
- Experience building production data systems or analytics platforms
- Experience building LLM applications in production
- Strong understanding of RAG systems
- Strong understanding of structured generation (schemas, JSON outputs)
- Strong understanding of tool use / function calling
- Strong understanding of agent workflows
- Awareness of failure modes in LLM reasoning (critical in finance)
- Experience with time-series data
- Experience with event-driven pipelines
- Experience with analytics / observability systems
- Comfort working with imperfect, high-volume financial data
- Experience in asset management / hedge funds / fintech
- Experience in portfolio analytics or risk systems
- Experience in trading / market data infrastructure
- Familiarity with exposure/risk models
- Familiarity with PnL attribution systems
- Familiarity with BI / analytics platforms for finance
- Experience with vector databases or hybrid retrieval systems
Qualifications
Must Haves
- 3–7+ years in backend, data engineering, or ML systems
- Strong Python (mandatory)
- Experience building production data systems or analytics platforms
- Experience building LLM applications in production
- Strong understanding of RAG systems
- Strong understanding of structured generation (schemas, JSON outputs)
- Strong understanding of tool use / function calling
- Strong understanding of agent workflows
- Awareness of failure modes in LLM reasoning (critical in finance)
- Experience with time-series data
- Experience with event-driven pipelines
- Experience with analytics / observability systems
- Comfort working with imperfect, high-volume financial data
Nice to Haves
- Experience in asset management / hedge funds / fintech
- Experience in portfolio analytics or risk systems
- Experience in trading / market data infrastructure
- Familiarity with exposure/risk models
- Familiarity with PnL attribution systems
- Familiarity with BI / analytics platforms for finance
- Experience with vector databases or hybrid retrieval systems
