AI Engineer

About Overdrive

Overdrive is an Intelligence Studio built to reimagine how people work. We've become the go-to automation partner for venture capital firms, modernizing deal flow, reporting, and operations, while also expanding our impact across other sectors.

We build AI-powered systems that close integration gaps and eliminate workflow debt across industries such as healthcare, financial services, construction, manufacturing, and non-profits. Our work spans horizontally across key enterprise functions — from HR and sales to finance and operations, helping teams move faster and work smarter.

At Overdrive, we work like a Formula 1 pit crew — fast, precise, and perfectly in sync. Every engineer plays a key role in fixing what's broken, tuning what works, and accelerating what's next.

You'll join a crew that values mentorship, hands-on building, and continuous learning in a remote-first environment where innovation meets execution.

Our Values

1. Build machines, not band-aids
   – We solve at the system level.
2. Cultivate our crew
   – We mentor, learn, and grow together.
3. Pit stop perfection
   – Fast, reliable, high-quality delivery.
4. Fun in the fast lane
   – We love what we do, and we bring the energy.

Role Overview

We're looking for an AI Engineer who can design and deliver production-grade AI agents, enterprise RAG systems, and MCP integrations.

This role is about building with purpose, owning critical components from architecture to deployment while ensuring our systems are secure, scalable, and enterprise-ready.

You'll set the standard for how we build at Overdrive: establishing patterns, reviewing code, mentoring teammates, and ensuring everything we ship meets the high standards of the enterprises we serve.

Key Responsibilities:

• Architect and build AI agents using LangGraph or similar frameworks (multi-step orchestration, tool use, error handling, guardrails, evaluation).
• Design and deploy enterprise RAG systems: embedding pipelines, vector databases, retrieval strategies, and performance optimization.
• Implement MCP servers/integrations that connect agents with enterprise systems (HRIS, CRM, ERP, DMS, data warehouses) — ensuring security, scale, and observability.
• Deliver production code with tests, CI/CD, monitoring, and tracing; define reliability standards (SLIs/SLOs).
• Partner with product and client-facing teams to translate enterprise requirements into robust AI architectures.
• Develop reusable components, templates, and internal playbooks to accelerate delivery across projects.
• Contribute to internal and open-source repositories (examples, docs, reference implementations) to showcase engineering strength.
• Drive security-by-design and cost-aware engineering across LLM pipelines and deployments.
• Mentor peers, lead technical reviews, and champion best practices in testing, evaluation, and MLOps.

Qualifications & Experience

Required (Must-have)

• 3+ years of engineering experience (strong foundation in backend and AI systems).
• Deep understanding of
  LangGraph
  and
  LangChain
  frameworks.
• Proven experience building and deploying
  RAG chatbots and agents
  into production.
• Ability to parse, embed, store, and retrieve data from documents efficiently.
• Understanding of
  vector databases
  , re-ranking, and retrieval optimization.
• Experience managing
  authentication, user flows, and production deployment
  (any cloud — AWS, GCP, or Azure).
• Demonstrated ability to
  architect AI workflows
  connecting multiple agents and tools.
• Strong programming skills in
  Python
  (priority language).
• Solid foundation in
  data structures, APIs, and system design principles
  .
• Proven
  MCP server/integration expertise
  , delivering connectors for enterprise systems with proper security and observability.
• Experience with
  vector databases
  (FAISS, Pinecone, pgvector, Weaviate) and embedding/LLM providers (OpenAI, Anthropic, Azure).
• Strong foundation in
  testing, CI/CD, containers (Docker)
  , and cloud infrastructure (AWS/GCP/Azure).

Preferred (nice-to-have)

• Experience working with large datasets (10–20GB+), signaling enterprise-level problem solving.
• Experience with medium to large enterprises, understanding reliability, compliance, and adoption expectations.
• Full-stack capability ) to extend automations into dashboards and client-facing apps.
• Great communicator, comfortable in client-facing technical discussions.
• Background in security/compliance (SOC2, GDPR, HIPAA) and enterprise readiness.
• Experience in regulated or high-stakes industries (finance, healthcare, HR tech, legal).
• Experience using TypeScript or in addition to Python.
• Familiarity with MCP servers, Composio, or multi-agent orchestration tools.
• Experience designing multi-agent graphs in LangGraph.
• Background working with startups or fast-paced, early-stage environments.
• Prior experience with Supabase or Postgres optimization.
• Familiarity with orchestration and automation tools (n8n, Make, Airflow, dbt).

Sample Tech Stack

• Agents/LLMs:
  LangGraph (or equivalent), OpenAI/Azure OpenAI, Anthropic
• RAG:
  FAISS, Pinecone, pgvector, Weaviate
• Pipelines/Orchestration:
  Python, FastAPI, n8n/Make
• Infrastructure:
  AWS/GCP/Azure
• Data:
  Postgres, S3/GCS, Airbyte/Fivetran (nice to have)

Why Join us?

• Work from anywhere, build everywhere.
• Thrive in a remote-first environment that values flexibility, ownership, and trust over time clocks.
• Contribute directly to building AI products and automation frameworks used by leading organizations worldwide.
• Learn alongside AI engineers, data scientists, and systems architects pushing the boundaries of automation and human potential.
• Work across venture and enterprise sectors, solving real problems that redefine how people work.

Our Hiring Process

• Resume Review:
  We assess alignment with AI agent, RAG, and MCP experience.
• Screening Call:
  Technical + behavioral; discuss recent hands-on projects and approach.
• T
  ech Assessmen
  t: Live walk-through of RAG architecture and design + Take home assessment
• Partner Call: Review your solution, discuss trade-offs, and explore mutual fit.
• Offer: If the right fit, we'll invite you to join our Pit Crew.

Inclusion Powers Innovation

We welcome applicants from all backgrounds and lived experiences.
Inclusion is our starting line
— when people feel safe to learn and contribute, they drive innovation. If you need accommodations at any stage, we'll support you.

How to Apply

Email your
resume
and
portfolio/GitHub
to
Rafael
at