AI / ML Engineer
Architect intelligent product features – LLM integrations, RAG pipelines, and production AI systems with guardrails and observability.
About the role
We are seeking a world-class AI / ML Engineer to lead the design and integration of intelligent features into client products. You will bridge the gap between cutting-edge AI research and production-grade engineering – shipping LLM-powered features that work reliably at scale.
In this role, you aren't just calling OpenAI APIs – you are architecting RAG pipelines, evaluation frameworks, guardrails, and observability stacks that make AI features trustworthy in enterprise environments.
You'll operate with high autonomy on client engagements, often serving as the technical authority on AI feasibility, architecture, and delivery timelines.
Core responsibilities
- LLM integration: Design and ship LLM-powered features using OpenAI, Claude, or open-source models — with proper error handling, fallbacks, and cost controls.
- RAG pipelines: Build retrieval-augmented generation systems with vector search, document chunking, and relevance tuning for client knowledge bases.
- Agentic systems: Implement multi-step AI agents and autonomous workflows that integrate with existing product APIs and business logic.
- Evaluation & guardrails: Create prompt testing suites, output validation, content moderation, and quality metrics for production AI features.
- Observability: Instrument AI features with latency, token cost, and quality tracking — dashboards clients can trust.
- Client advisory: Advise on AI feasibility during discovery, scoping realistic MVPs, and setting expectations with stakeholders.
What we're looking for
We are looking for an engineer who has shipped AI features to production and understands the gap between demos and reliable systems.
Technical mastery
- →Production LLM experience: Hands-on with OpenAI, Anthropic, or open-source models in real products — not just notebooks.
- →RAG & vector search: Experience with LangChain, LlamaIndex, Pinecone, pgvector, or similar retrieval stacks.
- →Python backend: Strong FastAPI or Django skills for serving ML workloads with proper async patterns.
- →Evaluation frameworks: Building test suites for prompt quality, hallucination detection, and regression testing.
- →Cost & latency optimization: Caching strategies, model routing, and batching for production efficiency.
Professional attributes
- →Pragmatic innovator: You know when AI is the right tool — and when a simple rule engine is better.
- →Clear communicator: Able to explain AI limitations and trade-offs to non-technical clients.
- →Security-minded: Understands data privacy, PII handling, and prompt injection risks.
- →Self-directed: Comfortable owning AI workstreams end-to-end on client projects.
Why you'll love working with us
Cutting-edge work
Ship AI features for real clients – copilots, document processing, intelligent search – not internal demos.
Remote & flexible
Work globally with an async-friendly team that respects deep focus time.
Learning budget
Stay current with rapidly evolving AI tooling through courses, conferences, and experimentation time.
Competitive pay
Top-of-market compensation for engineers who deliver production AI, not prototypes.
How to apply
Please follow this application process carefully. Applications without the requested video will be archived.
- 1Email contact@geniusxlab.com with the subject line "AI / ML Engineer." First line: "I ship AI to production."
- 2Include links to GitHub, papers, or products featuring your AI work.
- 3Attach your résumé in PDF format.
Video application (Loom, max 5 minutes)
- Question 1 — Production AI
Describe an AI feature you shipped to production. What broke, how did you fix it, and what would you do differently?
- Question 2 — RAG architecture
Walk us through how you would design a RAG system for a client with 10,000+ documents. What are the key decisions?
- Question 3 — Agentic patterns
How do you use AI agents in your daily workflow? Give a specific example of an autonomous pattern you've implemented.