Back
Forward Deployed ML Engineer, Agents
Full-time
Aion is the enterprise AI platform, a full-stack solution for building, fine-tuning, and deploying AI at scale. As a Forward Deployed ML Engineer, Agents, you'll work in small teams to own delivery of high-stakes customer projects, embedding directly at client sites to architect, build, and deploy intelligent agent solutions.
Who You Are
A hands-on AI engineer with 3-5+ years building production-grade multimodal AI systems and LLM applications. You're comfortable writing production code, presenting technical solutions to C-level executives, and debugging complex AI systems. You've shipped voice agents, video processing systems, or conversational AI to production, and you thrive translating ambiguous business requirements into concrete technical solutions.
What You'll Do
Customer Engagement & Multimodal Agent Development
Work directly at customer sites conducting discovery workshops and technical assessments to identify high-impact AI opportunities.
Design and architect end-to-end multimodal agent systems (voice + video + text).
Build production-grade voice AI systems using STT, TTS APIs, and LLMs.
Develop vision-enabled agents processing real-time video streams.
Implement multi-agent orchestration with frameworks like LangChain or LlamaIndex.
Rapidly prototype POCs in 2-4 weeks, coding alongside client teams.
Optimize for sub-500ms latency, natural conversation flow, turn detection, and interruption handling.
Integrate agents into customer codebases via REST/GraphQL/WebSocket APIs and custom SDKs (Python, TypeScript).
Data Strategy & MLOps Infrastructure
Design data architectures with efficient processing and ingestion pipelines for training and inference.
Implement RAG systems with vector databases, optimizing embedding strategies, chunk sizes, and retrieval methods.
Prepare and validate datasets for fine-tuning, evaluation, and synthetic data generation.
Work with MLEs, MLOps, and SREs on model deployment and productionization.
