Terrabase

We're building an AI interface that helps enterprises make instant decisions from fragmented data. Our platform connects multiple enterprise data sources and leverages specialized AI agents to enable faster, smarter business decisions. Role: As an AI Engineering Intern at Terrabase, you'll work directly with our founding team to improve our AI agents through prompt engineering, testing, and optimization. This role offers hands-on experience with cutting-edge AI technologies in a fast-paced startup environment. Type: Paid Internship, Remote Responsibilities: Design and optimize prompts for specialized AI agents across different enterprise use cases Evaluate and improve search relevance in document retrieval systems Test and benchmark different LLM approaches for enterprise workflows Help develop evaluation datasets for measuring agent performance Build simple demos and prototypes to showcase agent capabilities Document best practices for prompt engineering and AI agent optimization Stay up-to-date with the latest developments in LLMs and agent frameworks Requirements: Currently pursuing a degree in Computer Science, Data Science, or a related field Demonstrated skill in complex problem-solving, algorithmic thinking or system design Strong Python programming skills Experience with LLMs and prompt engineering (personal projects qualify) Familiarity with web technologies and API integration Self-motivated with a willingness to take ownership of tasks A passion for AI applications and product development Nice to Have: Experience with LangChain, LangGraph, or similar frameworks Knowledge of semantic search and vector databases Familiarity with enterprise systems (ERPs, CRMs) Contributions to open-source AI projects Previous internship experience in AI/ML fields Terrabase is an Equal Opportunity Employer. We celebrate diversity and are committed to creating an inclusive environment for all employees. Show more Show less

Experience: Two to five years building production Python backends About Terrabase Terrabase cuts hours of manual analysis to seconds. Our AI agents find the answer and trigger the next workflow automatically. Your work keeps that engine reliable, fast, and secure for enterprise customers. Why this role matters Every AI insight we deliver passes through a Python service you will own. Low-latency APIs, resilient task queues, and rock-solid observability make the difference between user delight and churn. You will design and scale that backbone. What will you do Build FastAPI services that expose search, retrieval, and orchestration endpoints. Scale async jobs with Celery and RabbitMQ, using Redis for caching and rate control. Containerize with Docker and deploy repeatably on EC2 using Terraform or similar tooling. Monitor with Prometheus, Grafana, and alerting hooks; chase p99 latency and error budgets. Automate CI and CD so every merge ships safely and rolls back cleanly. Harden security, secrets management, and SOC two logging. Document clear run books and post-mortems so anyone can debug at two in the morning. Collaborate with AI and front-end teams to hit sub-second query times and zero downtime releases. What we look for Two to five years of writing clean, idiomatic Python in production. Strong work ethic and bias for ownership. You identify problems, propose fixes, and drive them to closure. Clear, systematic thinker. Your design docs read like thinking in public, and your code structure reflects first principles reasoning. Proficient Python engineer comfortable with type hints, pytest, and modern packaging. Proven FastAPI or similar web framework expertise. Hands-on experience with Celery, RabbitMQ, and Redis at meaningful scale. Confident with Docker, Linux networking, and AWS EC2 fundamentals. Solid grasp of monitoring, tracing, and log aggregation. Clear communicator who values concise design docs and thoughtful code reviews. Bonus points Experience meeting SOC two or HIPAA audit requirements. Prior work on high-throughput data pipelines or vector stores. Contributions to open-source backend or DevOps projects. Life at Terrabase We are a sharp, humble, fully remote crew that values deep focus and fast feedback. Your code reaches real customers every week, backed by generous AWS budgets and a culture that favors clear thinking over long meetings. Terrabase is an equal opportunity employer. We celebrate diversity and are committed to building an inclusive environment for every team member.

Experience: Two to five years of shipping production AI or machine-learning systems and scaling data-intensive back ends. Why this role matters Terrabase is shaping the next frontier of work AI—an adaptive platform where ambient and specialized agents mesh seamlessly to deliver the one answer that matters, instantly and safely. Think category-defining speed, unwavering accuracy, and enterprise-grade guardrails. Your mission: harden that edge with bulletproof eval loops, unbreakable safety nets, and ruthless performance tuning across our multi-agent engine. What will you do Own the evaluation loop: Design offline and real-time test harnesses, golden-set datasets, and automated regression dashboards that grade each new agent release on precision, recall, latency, and cost. Harden safety and guardrails: Implement content filters, prompt firewalls, and fallback chains so answers stay compliant with SOC 2 and HIPAA constraints. Optimize prompts and retrieval: Iterate on system, user, and tool prompts for diverse enterprise workflows. Tune ranking models and vector search parameters to lift relevance. Benchmark LLM approaches: Compare open-weight models, hosted APIs, and fine-tuned derivatives. Present trade-off reports that balance performance with budget. Prototype and demo: Build thin, focused proof-of-concepts that show customers new capabilities before we commit to full sprint cycles. Document and share best practices: Write concise run-books, design notes, and post-mortems so the next engineer can reproduce your results without guesswork. Stay current: Track the latest research on retrieval-augmented generation, tool-calling agents, and evaluation methodologies; bring the most practical ideas into production. What we look for Two to five years of building or operating machine learning or data-intensive back-ends in production. Strong work ethic and bias for ownership. You identify problems, propose fixes, and drive them to closure. Clear, systematic thinker. Your design docs read like thinking in public, and your code structure reflects first principles reasoning. Proficient Python engineer comfortable with type hints, pytest, and modern packaging. Hands-on experience with at least one of: LangChain, LangGraph, or other agent frameworks. Familiarity with vector databases and semantic search fundamentals. Evidence of structured problem solving: could be a design doc, a refactored subsystem, or an open-source pull request. Clear communication and bias for action—you unblock yourself and raise flags early. Bonus points Prior work with evaluation libraries such as Ragas, LM-Eval, or Intercode. Experience integrating compliance guardrails or red-team testing for Gen-AI systems. Contributions to open-source AI projects or published technical blogs. Life at Terrabase We operate as a sharp, humble, fully remote crew that values deep focus and fast feedback. Your code ships to real customers every week, supported by generous GPU budgets and a culture that prizes clear thinking over long meetings. Terrabase is an equal opportunity employer. We celebrate diversity and are committed to building an inclusive environment for every team member.

Experience: 3–5 years building production backend infrastructure and deployment systems About Terrabase Terrabase turns hours of manual enterprise analysis into seconds. Our AI agents retrieve insights and trigger downstream workflows automatically. Your job is to ensure the systems they run on are fast, fault-tolerant, and built to scale. Why this role matters Every enterprise-grade AI workflow relies on a secure, scalable, and observable platform. You will own the infrastructure and backend services that power our AI agents — from deployment pipelines to API gateways. Your work ensures that insight delivery is not only fast but also reliable, compliant, and production-hardened . What you’ll do Architect and maintain FastAPI-based services for search, orchestration, and data workflows Design scalable async pipelines with Celery and RabbitMQ, integrating Redis for caching and throttling Define and manage IaC (Terraform or Pulumi) for reproducible deployments on AWS (primarily EC2) Build robust CI/CD pipelines that enable safe deploys, canary releases, and automatic rollbacks Set up and fine-tune observability stacks (Prometheus, Grafana, Loki, Sentry) Implement security and secrets management , align systems with SOC 2 / HIPAA readiness Drive platform reliability: monitor p99 latencies, uptime SLAs, error rates, and cost optimizations Partner with AI and product engineers to deliver zero-downtime releases and support multi-tenant deployments Write postmortems, incident runbooks, and internal docs to raise team-wide resilience What we look for 3–5 years building production-grade Python backends and infrastructure Strong understanding of cloud-native deployments (AWS EC2, VPCs, Docker, Linux, networking) Deep experience with DevOps tooling — Terraform, CI/CD systems, secrets management Production experience with FastAPI (or similar), Celery, RabbitMQ, and Redis Solid grasp of observability patterns — metrics, logging, distributed tracing Bias toward ownership and clarity — you spot failure points early and automate fixes Strong communicator — from infra diagrams to deployment docs, you keep teams aligned You think like a systems engineer: composability, scalability, debuggability Bonus points Experience building HIPAA or SOC 2 -compliant platforms Contributions to platform-focused open source (e.g., Celery, FastAPI, Terraform) Past work scaling vector databases , search infra, or high-throughput pipelines Life at Terrabase We're a sharp, humble, remote-first team that values clarity and shipping. We move fast without breaking trust, backed by strong automation, clean infra, and real-time visibility into production. You’ll have ownership, real customer impact, and a platform worth building.