Get a reply from this employer
Your resume and cover letter, tailored to exactly what they’re hiring for.
Cloud Science Labs is seeking a software engineer to build core AI agents using TypeScript and AI SDKs. You will design decision logic for tool selection, build document-understanding pipelines, and implement hybrid RAG retrieval with versioning.
You will contribute to an evaluation framework, guardrails, and continuous improvement from real usage, collaborating closely with backend teams in a fast-paced environment.
Build and own the core of Agent using the AI Agents SDK (TypeScript) and the hosted Agents API- agent instructions, tool orchestration, and per-conversation sessions.
Design the agent’s decision-making so it reliably understands requests in Chat and selects the correct tools to act on them.
Build document-understanding pipelines that extract requirements from files in any format, including scanned documents and images via OpenAI vision.
Implement retrieval (RAG) using hybrid search - pgvector embeddings plus PostgreSQL full-text - with sound chunking, versioning, and relevance tuning.
Define and maintain the AI evaluation framework: build eval sets from past projects, set per-wave accuracy targets, and enforce the evaluation gate in CI so quality never regresses.
Implement guardrails and prompt-injection defenses, ensuring all documents and messages are treated as data, never as instructions, and that the model performs language tasks only - never computing numbers, dates, or permissions.
Deliver multilingual understanding, including mixed-language conversations, with consistent, correct responses.
Continuously review agent accuracy against saved guidance, and improve the system from real usage.
1-2 years of software engineering experience, including real, production-shipped work on LLM agents with tool/function calling (AI Agents SDK, LangGraph, or equivalent).
Hands-on RAG expertise: embeddings, vector search (pgvector or similar), chunking, and retrieval-quality optimization.
A rigorous, demonstrable approach to evaluation and guardrails - able to explain how agent accuracy is measured and how hallucinations and prompt injection are prevented.
Working knowledge of PostgreSQL and API integration.
Strong analytical skills, clear written communication, and the ability to work closely with the backend team.
Nice to have: OpenAI vision/classification pipelines, MCP (Model Context Protocol) experience.
Life at CSL
What makes us different and why you'll love it here.
We embrace cutting-edge tech and creative problem-solving
Cross-functional teams working as one, globally
Continuous learning, mentorship, and career advancement