Senior AI/ML Engineer – Agentic Systems & Platforms

About the role

We are seeking a senior AI/ML engineer to lead the design, development, and deployment of agentic AI systems that transform patient journeys. You will work at the cutting edge of generative AI, building autonomous multi‑agent workflows and platforms that directly improve healthcare outcomes.

Key responsibilities

• Architect, build, and deploy production‑grade multi‑agent systems (ReAct, plan‑and‑execute, tool‑augmented reasoning, stateful collaboration).
• Develop user‑facing platforms that enable non‑engineers to create, test, and launch custom AI agents.
• Design resilient, low‑latency microservices and pipelines that integrate foundation models with internal systems, vector databases, and external data sources.
• Implement LLMOps, evaluation, benchmarking, guardrails, and tracing pipelines to monitor hallucination rates, tool usage accuracy, and cost/latency trade‑offs.
• Ensure AI safety, determinism, data privacy, and security in a regulated healthcare environment.
• Provide technical leadership by benchmarking and integrating state‑of‑the‑art open‑source and proprietary models.

Required profile

• 8–10+ years of professional software engineering experience building scalable, distributed systems.
• 5+ years developing, fine‑tuning, and deploying ML models, with at least 2 years focused on LLMs, generative AI, and agentic frameworks.
• Hands‑on experience with modern agent orchestration frameworks such as LangGraph, AutoGen, CrewAI, LlamaIndex, or custom in‑house engines.

Required skills

• Python
• FastAPI
• Rust
• Go
• Microservices, event‑driven and async processing architectures
• Vector databases: Qdrant, Pinecone, Weaviate
• Hybrid search, semantic caching, dynamic context/memory management
• LLMOps, model benchmarking, guardrail implementation