Summary
✨ AI‑Generated
Join a small, fast-moving AI engineering team and build production-facing applications powered by large language models. You will work on retrieval-augmented generation, structured outputs, tool-calling agents, multi-agent workflows, memory, planning, human-in-the-loop systems, and model evaluation. This is a practical engineering role focused on shipping features rather than research-only work.
Highlights
Hands-on internship with direct exposure to production AI infrastructure, real users, LLM-powered applications, agentic systems, evaluation, and modern AI engineering practices.
Description
About the company
SKXYWTF builds Exponential Yield (XY) financial products with a social and sustainable mandate — maximising returns while advancing market equity.
We sit at the intersection of quantitative finance and applied AI.
The role
You'll join a small, fast-moving AI engineering team working on next-generation language model applications and agentic systems.
This is hands-on product engineering — not research busywork — with direct exposure to production AI infrastructure and real users.
What you'll work on
Build and ship features for LLM-powered products, including RAG pipelines, structured output layers, and tool-calling agentsDesign and integrate agentic workflows using orchestration frameworks (LangGraph, LlamaIndex, or similar)Design and implement multi-agent systems with memory, planning, and human-in-the-loop capabilities using frameworks such as LangGraph, AutoGen, or CrewAI.Work with model evaluation frameworks — write evals, run benchmarks, and iterate on prompt engineeringBuild and maintain observability tooling: tracing, logging, and latency monitoring for AI inference in productionContribute to model context management — chunking strategies, embedding pipelines, vector store integrationParticipate in code reviews, architecture discussions, and documentationWhat we're looking for
Currently pursuing a BS or MS in Computer Science, Engineering, or a related fieldSolid Python fundamentals; experience with TypeScript, Go, or Rust is a strong plusFamiliarity with LLM APIs (OpenAI, Anthropic, Gemini, or open-source equivalents via Ollama/vLLM)Exposure to RAG patterns, vector databases (Pinecone, Weaviate, pgvector), or embedding workflowsWorking knowledge of containerisation (Docker) and comfort with cloud environments (AWS / GCP / Azure)Understanding of agentic patterns: tool use, function calling, ReAct loops, multi-agent coordinationFamiliarity with model evaluation concepts — LLM-as-judge, benchmark design, RAGAS or similarExcellent communicator; can write clearly and discuss tradeoffs in technical reviewsCuriosity-driven — you read release notes, follow model launches, and have opinions about context windowsCore stack
Python
REST / async APIs
Docker
Git
SQL
AI / ML layer
LLM APIs
RAG pipelines
Vector DBs
Prompt engineering
LangChain / LangGraph
LLM evals
Structured outputs
Agentic workflows
Nice to have
TypeScript
React / Next.js
Kubernetes
OpenTelemetry / tracing
Fine-tuning (LoRA / QLoRA)
MCP servers
Solidity / Web3
ℹ
Unpaid internship · 3 months.
This is a pre-revenue startup engagement.
Interns gain direct production experience, mentorship, and a verifiable portfolio of shipped AI systems.
