AI Engineering Intern

About the job

Who We Are

Bynd is redefining financial intelligence through advanced AI, transforming how leading investment banks, private equity firms, and equity researchers globally analyze and act upon critical information. Our founding team includes a Partner from Apollo ($750B AUM) and AI engineers from UIUC, IIT, and other top-tier institutions. Operating as both a research lab and a product company, we build cutting-edge retrieval systems and AI-driven workflow automation for knowledge-intensive financial tasks.

Role Overview

We're hiring a AI Engineering Intern to design and build the systems that power Bynd's AI-native financial intelligence platform. You'll work closely with the founding team, product, and AI engineers to shape how financial data is processed, secured, and delivered to enterprise users. You will build and iterate on production-grade LLM driven features, designing reliable workflows that include multi-step orchestration, structured outputs, and rigorous evaluations. You'll move fast, prototyping quickly then hardening code with robust logging, monitoring, and tests.

Responsibilities

• Build LLM-powered backend features that ship to real users.
• Design reliable workflows: multi-step orchestration, structured outputs, guardrails, and evals.
• Translate user needs into precise system behavior alongside product and engineering teams.
• Leverage modern AI coding tools (Cursor, Claude Code) to maintain high developer velocity and quality.

Qualifications

Must-haves:

Strong grasp of Data Structures & Algorithms (trees, graphs, DP) and systems basics (networking, HTTP, concurrency).

High proficiency in Python. Experience with REST APIs, background jobs, and SQL (Postgres).

Proven experience building real-world apps where LLMs are core.

You should be comfortable with :

• Prompt engineering as a discipline (versioning, templates)
• Function/tool calling & schema-constrained JSON outputs.
• Multi-step workflows
• Basic evaluation approaches and regression checks.

Preferred:

• TypeScript/Node Proficiency
• Experience with Agent SDKs (OpenAI tool calling, LangGraph, Claude tool use, etc.) with custom reliability layers.
• Workflow automation projects (document pipelines, task orchestration) that are robust and built with logic, not just plug and play.
• Familiarity with Docker, CI/CD, and cloud services.
• Observability experience (structured logs, tracing, metrics).

What We're Looking For

We are looking for projects / experience where you made LLMs reliable:

• LLM-driven triage or extraction systems with validations/retries.
• Structured extraction with JSON schemas + evals.
• RAG systems that ground responses with provenance.
• Agents using tools (APIs, DBs) with deterministic control flows.

What We Offer

Competitive compensation and meaningful equity

Direct product influence with global financial institutions as your customers

Opportunity to work at the cutting edge of generative AI research and application

Collaborative, ambitious, and supportive team environment