LLM Engineer - 2

Role overview

LLM Engineer - 2 at InfoCusp Innovations

The Senior LLM Engineer will lead the design, development, and deployment of complex, autonomous agentic AI solutions within production environments, working across multi-agent frameworks and orchestrating large language models.

The position is or scalable applied AI, with a focus on delivering robust and fair agentic systems that deliver organizational value, autonomy, and operational efficiency.

Responsibilities

• Architect, design, and deploy scalable agentic AI systems that coordinate LLMs, multi-agent collaboration, and external tool integrations through advanced tool calling.
• Develop, maintain, and optimize AI-driven pipelines utilizing frameworks such as LangGraph, ADK and LangChain, enhancing data inference and orchestration.
• Integrate agentic AI solutions into enterprise workflows, automating complex business functions (e.g., customer service, supply chain, decision support).
• Proactively address system evaluation, debug AI agent workflows, and ensure compliance with emerging regulatory and ethical guidelines.
• Promote security, transparency, fairness, and reliability across all deployed agentic systems.
• Mentor junior engineers, contribute to cross-functional teams, and champion the adoption of state-of-the-art LLM technologies and practices.
• Requirements At least 1 year of experience with LangGraph (must have) 4+ years of overall experience working on industry projects Experience with LangChain, and other agentic orchestration frameworks.
• Deep proficiency in designing and deploying multi-agent frameworks and sophisticated tool-calling or API orchestration pipelines.
• Design and implement continuous monitoring systems for autonomous AI agents, ensuring performance, reliability, adherence to ethical guardrails, and optimal cost/latency in production.
• Develop and execute scalable LLM evaluation methodologies (including code-based, LLM-as-a-Judge) to rigorously assess model quality, safety, and goal alignment.
• Proficiency in Python Familiarity with retrieval-augmented generation (RAG) and modern vector databases (Pinecone, Weaviate).
• Experience with cloud platforms (AWS, GCP, Azure), MLOps practices, and production-grade deployment.
• Strong understanding of data privacy, model security, and compliance with current AI regulations and frameworks.

Preferred qualifications and skills

• Experience with Hugging Face, Neo4j, or knowledge graphs.
• Background in autonomous decision-making systems, anomaly detection, and dynamic process optimization.
• Track record of publishing, presenting, or open-sourcing agentic AI innovations.
• Strong problem-solving aptitude, collaborative mindset, and excellent communication skills.

Employment details

• Location: Pune [India]