Lead Ai Engineer

Job Description

· Leading, mentoring, and managing a team of AI Engineers - setting technical direction, reviewing architecture and code, and supporting their day-to-day growth.

· Driving the architecture of Tristone's agentic AI platform end to end, spanning agents, MCP servers, and supporting services that propose and apply changes across large codebases and financial workflows.

· Designing and overseeing retrieval systems (RAG, vector search, hybrid approaches) that give AI agents and developers accurate, up-to-date context from large codebases, financial documents, and design artifacts.

· Building and refining compile, test, and evaluation pipelines, covering static analysis, style and safety checks, performance gates, and code review, to consistently measure and raise the quality of AI-generated changes.

· Defining best practices around concurrency, telemetry, configuration hygiene, prompt versioning, and performance-sensitive code paths, so AI outputs remain reliable and idiomatic.

· Driving experiments and evaluation frameworks to continuously improve AI-driven workflows across the team.

· Acting as the primary point of technical escalation for the AI engineering function, liaising with the MD and cross-functional stakeholders on priorities, timelines, and risk.

· Complying with IT policies and procedures.

· Maintaining security of information at all times.

Requirements

· 4+ years of overall engineering experience, including demonstrable experience building and shipping AI/LLM-powered systems.

· Prior experience leading, mentoring, or managing engineers, or clear readiness to step into a team-lead role.

· Strong proficiency in Python (Java a plus), with hands-on experience in production-grade software systems.

· Proven experience with agentic AI frameworks and patterns (LangChain, LangGraph, AutoGen, CrewAI, or similar) and multi-agent orchestration.

· Practical experience with retrieval systems - vector search, embeddings, RAG pipelines, or hybrid retrieval approaches.

· Experience with MCP (Model Context Protocol) servers or comparable tool/agent-integration architectures.

· Strong communication skills, with the ability to translate technical decisions for non-technical stakeholders and senior leadership.

· Comfort operating in a fast-paced, high-trust environment handling sensitive financial data.

Strongly preferred-

· Experience in fintech, financial services, or investment/deal-related domains (M&A, private equity, IPO due diligence, or similar).

· Familiarity with compiler/static analysis tools or large-scale refactoring systems.

· Experience fine-tuning or customizing open-weight models.

· Knowledge of model-serving infrastructure and evaluation/observability tooling for LLM systems.

· Exposure to security-conscious deployment practices (OWASP LLM Top 10, API hardening, audit logging).

Qualification-

• Bachelor’s or Master’s in Computer Science (or related) with strong fundamentals (algorithms, data structures, systems)
  

Requirements
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): 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)