Context Engineer (Investments)
A sample job description. Copy and adapt for your organization.
Mission
Turn the firm's unique knowledge, processes and data into a structured "context layer" that makes AI tools genuinely useful for discretionary PMs and analysts.
Reports to
Head of Equities / CIO (with a dotted line to Data / Tech)
Primary Stakeholders
Portfolio managers, sector analysts, quant / data science, data engineering, risk.
Key Responsibilities
Map the firm's "context"
- Document investment processes, taxonomies, playbooks and sector nuances.
- Catalogue internal data sources (notes, models, CRM, research, risk data) and how they're used.
Design and maintain the investment ontology
- Define entities (companies, themes, KPIs, catalysts) and relationships that matter for the firm.
- Work with quants / engineers to turn this into schemas, tags, and knowledge graphs.
Curate data for AI tools
- Work with data engineering to clean, normalise and tag internal documents and data.
- Define what should and should not be exposed to PM-facing AI tools (IP, compliance, PII).
Bridge PMs and technical teams
- Translate PM questions into data / product requirements.
- Prioritise use cases (earnings prep, idea tracking, risk questions, etc.) and test prototypes with PMs.
Guardrails, quality and governance
- Define quality standards for AI outputs (what "good" looks like for the desk).
- Work with compliance and risk on guardrails, logging, and review processes.
Evangelise and train
- Run small pilots with PMs, gather feedback, iterate.
- Create simple playbooks: "Top 5 ways to use the system this quarter."
Ideal Background
- 5–10 years in investment roles (PM/analyst) or strong familiarity with discretionary equity investing.
- Comfort with data and technology: can work with quants/data engineers, understands basics of databases/APIs.
- Experience in product / project / change management is a plus.
- Strong communication skills; can talk credibly with both PMs and engineers.
Success Metrics (Examples)
- Time saved per PM on core workflows (earnings prep, monitoring, reporting).
- Adoption: % of PMs/analysts regularly using AI tools embedded with the firm's context.
- Number of high-value workflows successfully "context-enabled".
- PM satisfaction scores: "Does this system reflect how we invest?"