AI Engineer

About the Role

We are seeking a highly skilled Agentic AI Engineer to architect, develop, and operationalize advanced agentic AI systems for enterprise-grade, healthcare-focused applications. This role requires deep technical expertise in Python, agentic AI frameworks (LangChain, LangGraph, AutoGen), RAG pipelines, and LLM integration. You will design multi-agent systems, build intelligent automation workflows, and ensure compliance with healthcare and enterprise governance standards.

Key Responsibilities

1.Agent Development & Architecture

• Design and implement autonomous AI agents using frameworks such as LangChain, LangGraph, AutoGen, or equivalent tools.
• Build scalable multi-agent systems capable of advanced reasoning, decision support, workflow automation, and secure tool usage.
• Develop agent memory systems, state management, and safe orchestration patterns to support complex, long-running workflows.
• Implement tool-use capabilities, structured decision-making, and chained reasoning for enterprise-grade workloads.

2. RAG & LLM Engineering

• Architect and optimize Retrieval-Augmented Generation (RAG) pipelines using vector databases (Pinecone, FAISS, Chroma, etc.).
• Implement embeddings workflows, retrieval logic, chunking strategies, and context management techniques.
• Perform LLM integration, fine-tuning, domain alignment, and safety enhancement (toxicity filtering, bias mitigation, guardrails).
• Develop prompt engineering frameworks, dynamic prompt chaining, and context-aware LLM orchestration.

3. Application & System Development

• Build robust Python-based microservices, APIs, and orchestration layers for agent interactions and inference flows.
• Containerize and deploy AI systems using Docker/Podman and cloud-native architectures (Kubernetes or equivalent).
• Ensure high availability, performance optimization, and reliability across AI services and pipelines.
• Create secure and scalable backend components enabling real-time inference and agent coordination.

4. Governance, Observability & Compliance

• Implement telemetry, monitoring, and observability for agent behavior and LLM performance using OpenTelemetry, Prometheus, ELK, or similar tools.
• Conduct model evaluation, safety checks, robustness tests, and audit procedures for agentic workflows.
• Operate within enterprise AI governance frameworks to ensure compliance with HIPAA, PHI protection, data security, and responsible AI guidelines.

5. Cross-Functional Collaboration

• Collaborate closely with Data Science, MLOps, Cloud Engineering, Compliance, and Product teams.
• Participate in architecture reviews, technical design discussions, sprint planning, and roadmap development.
• Document technical decisions, system architectures, and operational best practices.

Required Skills & Qualifications

Technical Expertise

• Strong proficiency in Python (advanced programming, clean architecture, asynchronous programming, API development).
• Hands-on experience with agentic AI frameworks such as LangChain, LangGraph, AutoGen, or similar tools.
• Solid understanding of RAG, embeddings, vector databases, retrieval strategies, and memory systems.
• Deep knowledge of LLMs, model integration, guardrails, and prompt engineering best practices.
• Experience with containerization (Docker, Podman) and cloud deployment workflows.
• Familiarity with monitoring and observability tools (OpenTelemetry, Prometheus, Grafana, ELK).
• Understanding of AI security, governance, compliance, and enterprise deployment standards.

Soft Skills

• Excellent debugging, analytical thinking, and problem-solving abilities.
• Strong communication and documentation skills.
• Ability to work collaboratively within cross-functional and multi-disciplinary teams.