At Insait, we build LLM-powered agents trusted by financial institutions and insurers — not demos, but live systems handling sensitive real-time conversations. Our agents run at scale across regulated environments, where reliability, compliance, and performance aren’t optional.

You'll lead the technical vision for our LLM platform — not just as a manager of people, but as an engineer who codes, optimizes, and shapes production systems from the inside out.

Where every decision you make impacts real-time agents deployed in the wild — handling sensitive, high-stakes conversations across financial institutions. If you're passionate about building systems that truly understand language, solving deep infra challenges — this is your playground.

• Lead the engineering team — Guide 4-6 ML and backend engineers building and operating LLM services at scale
• Design robust pipelines — Build fine-tuning workflows, automated evaluation systems, and safe rollback mechanisms for model updates
• Implement comprehensive testing — Create automated regression suites and load testing that catches issues before production
• Manage hybrid deployments — Deploy and maintain voice/chat agents across cloud infrastructure and secure on-premises environments
• Monitor system performance — Track cost optimization, latency patterns, and model drift with real-time alerting and intervention

• Hands-on LLM development experience — fine-tuning, prompt chaining, or running inference at scale
• 5+ years backend development — Proven experience building scalable Python services and microservice architectures
• Technical leadership background — Experience leading engineering teams, making architectural decisions, and mentoring developers
• Deep RAG expertise — Strong understanding of embeddings, vector search, prompt engineering, and retrieval-augmented generation patterns
• Workflow orchestration — Proficiency with Airflow, Prefect, or similar tools for managing complex data and ML pipelines
• Communication skills — Clear technical writing and verbal communication for cross-functional collaboration

• Computer Science degree or equivalent technical background
• Vector database experience — Practical work with Pinecone, Weaviate, or similar systems in GenAI applications
• Open source contributions — Demonstrated involvement in relevant ML, AI, or infrastructure projects
• Experience developing for and operating services on Amazon EKS, including Docker containerization, Helm, and CI/CD pipelines.

• Real impact: Build AI systems that financial institutions trust with critical customer interactions and business processes.
• Technical ownership: Shape the architecture and technical direction of production LLM systems serving thousands of users.
• Strong team: Work alongside experienced engineers who understand both the potential and practical challenges of deploying AI at scale.
• Growth opportunity: Join a company with proven product-market fit in a rapidly expanding market, with significant equity upside potential.