Ai Engineer

Job Description Role: Building & Owning the AI Agent Infrastructure Designing and deploying multi-agent systems for investment research, M&A due diligence screening, and FP&A automation using Python and frameworks like LangChain or CrewAI Setting up and managing a private cloud environment (AWS or Azure) where all AI workloads run ensuring client data never leaves Tristone’s controlled environment Building and maintaining an internal knowledge base (vector database) that indexes all past project work and makes it searchable by AI agents and analysts Integrating AI agents with external financial data sources using controlled API connections with rate limiting and audit logging Owning the prompt library: write, test, version-control, and continuously improve the prompts used by all agents Data Privacy & Security Architect a private LLM deployment self-hosted open-source models or private cloud instances so client data never passes through shared public APIs Implementing data classification: tag incoming data by sensitivity and enforce routing rules so confidential data only reaches approved private models Maintaining full audit logs of every AI agent action what went in, what model processed it, what came out, who accessed it Enforcing role-based access controls so analysts use AI tools within defined permissions Produce monthly privacy compliance reports for senior leadership Coordinating with External Development Partners Serving as Tristone’s technical point of contact for any outsourced developers or firms building AI modules Reviewing all code from external partners before deployment checking security, data handling, and quality Writing technical specifications that translate analyst workflow requirements into developer briefs Managing all code in a private GitHub repository with documentation Tristone always owns and controls the codebase Continuous Improvement & Fine-Tuning Monitoring AI agent outputs daily: track accuracy, hallucination rates, and analyst feedback then improve prompts and configurations Fine-tuning models on Tristone-specific financial language over time starting with prompt engineering, progressing to RAG, and eventually supervised fine-tuning Evaluating new AI tools monthly and recommend adoption where there is clear ROI Training & Supporting the Analyst Team Running onboarding sessions for analysts on how to use AI tools effectively practical, not theoretical Building a simple internal dashboard showing team AI usage and time saved per person Being the go-to person when an agent produces a wrong output diagnose it and fix it quickly Complying with IT policies and procedures Maintaining security of information at all times Requirements Non-negotiable Technical skills Skill What We Need Python (Advanced) Write clean, well-documented Python for data processing, API calls, and agent logic. Comfortable with virtual environments, error handling, and structuring reusable code. LangChain or CrewAI Build multi-agent pipelines: define agents, assign tools, chain tasks, handle agent memory and context.

At least one real project built with either framework — demonstrated via GitHub. LLM APIs (Claude / OpenAI / Open Source) Integrate with Claude or OpenAI API via Python. Understand token limits, system prompts, temperature, and structured output formatting.

Know when to use which model. Private / Self-Hosted LLM Deployment Deploy and run an open-source LLM (Llama 3, Mistral, or similar) on a private server or private cloud. Understand the security architecture required for financial data environments.

Vector Databases (RAG) Set up and query a vector database (Pinecone, ChromaDB, or Weaviate). Understand how RAG works — embedding documents, storing vectors, retrieving relevant context for LLM prompts. Data Security & Access Controls Implement API key management, role-based access, data encryption at rest and in transit, and audit logging.

Understand SOC 2 and ISO 27001 principles at a conceptual level. Cloud Platforms (AWS or Azure) Deploy applications on AWS or Azure: set up servers, manage storage, configure networking basics, monitor costs. Comfortable estimating and managing cloud spend.

Git & Version Control All code version-controlled in GitHub with clear commit history, branching, and documentation written for non-technical readers. Strongly Preferred skills (Weighted Heavily in Evaluation) : Skill Why It Matters at Tristone Financial services domain knowledge You will work daily with PE analysts, family office teams, and investment bankers. Understanding basic financial terminology (IRR, EBITDA, comps, LP/GP structures) is important.

CFA not required — but comfort in financial conversations is. PDF & document parsing Most financial data arrive as PDFs — annual reports, CIMs, DD reports. Experience with PyMuPDF, pdfplumber, or AWS Textract is a strong advantage.

Prompt engineering Writing good prompts is a craft. The difference between a useful AI output and a useless one is often the quality of the prompt design. n8n or Make (workflow automation) For automating workflows without code — connecting tools, scheduling agent runs, routing outputs. Power BI or Tableau Tristone builds financial dashboards for clients.

Basic dashboard skills allow you to connect AI outputs directly to client-facing visuals. Experience & Qualification- 2–4 years of hands-on software development at least 1 year working specifically with LLMs, AI agents, or NLP systems At least one AI project currently in production (used by real users, not a demo) you must be able to demonstrate this Degree in Computer Science, Engineering, or Mathematics or demonstrable self-taught capability evidenced by public GitHub work Strong written and spoken English, you will write technical documentation, analyst guides, and developer briefs Preferred Experience in financial services, fintech, or investment research Previous experience as a solo technical lead someone who has owned a project end-to-end, not just contributed Familiarity with data privacy regulations relevant to financial services (GDPR, India DPDP Act 2023, SOC 2 principles) Requirements Non-negotiable Technical skills Skill What We Need Python (Advanced) Write clean, well-documented Python for data processing, API calls, and agent logic. Comfortable with virtual environments, error handling, and structuring reusable code.

LangChain or CrewAI Build multi-agent pipelines: define agents, assign tools, chain tasks, handle agent memory and context. At least one real project built with either framework — demonstrated via GitHub. LLM APIs (Claude / OpenAI / Open Source) Integrate with Claude or OpenAI API via Python.

Understand token limits, system prompts, temperature, and structured output formatting. Know when to use which model. Private / Self-Hosted LLM Deployment Deploy and run an open-source LLM (Llama 3, Mistral, or similar) on a private server or private cloud.

Understand the security architecture required for financial data environments. Vector Databases (RAG) Set up and query a vector database (Pinecone, ChromaDB, or Weaviate). Understand how RAG works — embedding documents, storing vectors, retrieving relevant context for LLM prompts.

Data Security & Access Controls Implement API key management, role-based access, data encryption at rest and in transit, and audit logging. Understand SOC 2 and ISO 27001 principles at a conceptual level. Cloud Platforms (AWS or Azure) Deploy applications on AWS or Azure: set up servers, manage storage, configure networking basics, monitor costs.

Comfortable estimating and managing cloud spend. Git & Version Control All code version-controlled in GitHub with clear commit history, branching, and documentation written for non-technical readers. Strongly Preferred skills (Weighted Heavily in Evaluation): Skill Why It Matters at Tristone Financial services domain knowledge You will work daily with PE analysts, family office teams, and investment bankers.

Understanding basic financial terminology (IRR, EBITDA, comps, LP/GP structures) is important. CFA not required — but comfort in financial conversations is. PDF & document parsing Most financial data arrive as PDFs — annual reports, CIMs, DD reports.

Experience with PyMuPDF, pdfplumber, or AWS Textract is a strong advantage. Prompt engineering Writing good prompts is a craft. The difference between a useful AI output and a useless one is often the quality of the prompt design. n8n or Make (workflow automation) For automating workflows without code — connecting tools, scheduling agent runs, routing outputs.

Power BI or Tableau Tristone builds financial dashboards for clients. Basic dashboard skills allow you to connect AI outputs directly to client-facing visuals. Experience & Qualification- 2–4 years of hands-on software development at least 1 year working specifically with LLMs, AI agents, or NLP systems At least one AI project currently in production (used by real users, not a demo) you must be able to demonstrate this Degree in Computer Science, Engineering, or Mathematics or demonstrable self-taught capability evidenced by public GitHub work Strong written and spoken English, you will write technical documentation, analyst guides, and developer briefs Preferred Experience in financial services, fintech, or investment research Previous experience as a solo technical lead someone who has owned a project end-to-end, not just contributed Familiarity with data privacy regulations relevant to financial services (GDPR, India DPDP Act 2023, SOC 2 principles)