Job Description
ABOUT THE ROLE
A hands-on builder role at the intersection of AI engineering, automation, and systems integration. You will research, design, and ship AI-powered solutions that reduce manual effort, improve operational efficiency, and scale internal workflows. You work across multiple live projects simultaneously.
- AI Engineer — design and deploy LLM-driven pipelines, agents, and AI-integrated tools across business workflows.
- Automation Engineer — identify, build, and maintain automations that eliminate repetitive tasks and improve throughput.
- Integration Engineer — connect disparate systems, platforms, and APIs into cohesive, reliable workflows.
WHAT YOU’LL BE DOING
AI Engineering & LLM Integration
- Integrate LLMs (GPT-4, Claude, Gemini, etc.) into internal tools and business workflows via API.
- Design and maintain prompt systems: system prompts, structured outputs, chain-of-thought pipelines.
- Build RAG pipelines — connect knowledge bases, spec documents, and SOPs to AI agents for accurate context retrieval.
- Evaluate and reduce hallucinations; implement human-in-the-loop validation where needed.
- Stay current on model releases, capabilities, and best practices — apply them immediately.
Automation & Workflow Engineering
- Map existing manual workflows; identify and prioritize automation opportunities.
- Build end-to-end automation pipelines for repetitive tasks: data extraction, form-filling, cross-platform data transfer.
- Develop browser and desktop automations using Playwright, Puppeteer, or equivalent computer-use frameworks.
- Create internal tools — small scripts, utilities, and micro-applications that save time and reduce errors.
- Maintain and iterate on existing automations as workflows evolve.
Systems Integration
- Connect third-party platforms, carrier portals, and SaaS tools via APIs, webhooks, and automation middleware.
- Build and maintain integration workflows using n8n, Make, Zapier, or Power Automate.
- Architect modular, maintainable systems — clean inputs, reliable outputs, clear documentation.
- Troubleshoot integration failures and maintain system reliability.
AI Research & Tool Evaluation
- Research and benchmark emerging AI tools, agent frameworks, and automation platforms.
- Evaluate feasibility of new tools for real use cases; produce concise internal assessment reports.
- Build reusable prompt libraries, automation templates, and internal knowledge bases.
- Contribute to AI governance practices: output validation, bias checks, ethical use.
TECH STACK & TOOLS
- AI & LLM Platforms
- OpenAI / GPT-4o
- Anthropic Claude
- Google Gemini
- Open-Source LLMs - OpenClaw
- Agent & Automation Frameworks
- LangChain / LangGraph
- AutoGen / CrewAI
- n8n
- Make (Integromat)
- Zapier
- Power Automate
- Playwright
- Puppeteer
- Development & Tooling
- Python
- REST APIs
- Git / GitHub
- Postman
- Claude Code
- VS Code
- JSON / YAML
- Basic JavaScript
- RAG & Knowledge Systems
- Vector DBs (Pinecone / Chroma)
- RAG Pipelines
- Document Parsing
- Embeddings APIs
WHAT WE’RE LOOKING FOR
Education
- Bachelor’s degree in Computer Science, Software Engineering, Information Technology, Data Science, or Artificial Intelligence preferred.
- Equivalent demonstrated skills and a strong project portfolio are equally valued.
Core AI & Technical Skills
- Working knowledge of LLMs: context windows, token efficiency, model behavior, and limitations.
- Prompt engineering proficiency: zero-shot, few-shot, chain-of-thought, structured output, and agentic prompting.
- Experience calling AI APIs and building functional workflows around them.
- Python scripting for automation, API integration, and data handling.
- Hands-on experience with at least one automation platform (n8n, Make, Power Automate, or Zapier).
- Familiarity with RAG concepts, vector databases, and document-grounded AI systems.
- Basic understanding of AI agents, tool-use, and multi-step reasoning pipelines.
Advanced AI Knowledge (Good to Have)
- Awareness of latest model releases, benchmarks, and capability shifts across major AI providers.
- Exposure to agentic frameworks: LangGraph, AutoGen, CrewAI, or similar.
- Understanding of fine-tuning concepts, embeddings, and semantic search.
- Experience with computer-use or browser-control agents.
Mindset
- Research-first: actively follows the AI space, reads docs, tests new tools.
- Builder: ships working systems — not just plans them.
- Detail-oriented: meticulous about output quality, testing, and validation.
- Adaptable: comfortable with ambiguity and a fast-moving environment.
Experience
- Minimum 1 year of experience — skills and portfolio matter most.
- Personal projects, freelance work, coursework, or hackathon entries involving LLMs, agents, or automation all count.
KEY PERFORMANCE INDICATORS
- 30–60% reduction in manual processing time on automated workflows.
- Fast prototype-to-deployment velocity within sprint cycles.
- Consistent, low-error output quality across AI pipelines.
- High internal adoption rate and positive team feedback on built tools.
WORK MODEL
Hybrid Model: This position requires 4 weeks on-site for initial onboarding and training, followed by a transition to a standard hybrid schedule.
“We value the uniqueness and experience each individual brings to the organization.”
