Senior LLM Engineer

• Home/Jobs/Senior LLM Engineer
• Senior LLM Engineer
• Infocusp Innovations
• Ahmedabad / Pune
• 4+ years
• Today
• $34.9K–49.4K/yr
• Full-time
• Onsite

Skills Required

• LLM-as-a-Judge
• RAG
• LangChain
• Hugging Face
• LangGraph
• Python
• Pinecone
• Weaviate
• AWS
• GCP
• Azure
• MLOps
• Neo4j
• Knowledge Graphs

Description

Senior LLM Engineer role focused on designing and deploying autonomous agentic AI systems in production. Emphasis on scalable applied AI, multi-agent orchestration, and robust, fair systems that deliver organizational value.

Company: Infocusp Innovations

Role: Senior LLM Engineer (3+ years)

Location: Ahmedabad/Pune

Experience

• 3+ years role title requirement
• At least 1 year of experience with LangGraph
• 4+ years of overall experience working on industry projects
• Proficiency in Python
• Experience with LangChain and other agentic orchestration frameworks
• Experience with cloud platforms: AWS, GCP, Azure
• Experience with MLOps practices
• Strong understanding of data privacy, model security, and current AI regulations/frameworks

• Lead design, development, and deployment of complex autonomous agentic AI solutions in production
• Architect scalable agentic AI systems coordinating LLMs, multi-agent collaboration, and external tool integrations
• Develop, maintain, and optimize AI-driven pipelines for data inference and orchestration
• Integrate agentic AI solutions into enterprise workflows to automate customer service, supply chain, and decision support
• Address system evaluation, debug AI agent workflows, and ensure compliance with ethical and regulatory guidelines
• Promote security, transparency, fairness, and reliability across deployed systems
• Mentor junior engineers and contribute to cross-functional teams
• Champion adoption of state-of-the-art LLM technologies and practices

• Design and implement continuous monitoring systems for autonomous AI agents to ensure performance, reliability, ethical guardrails, and optimal cost/latency in production
• Develop and execute scalable LLM evaluation methodologies, including code-based and LLM-as-a-Judge approaches, to assess model quality, safety, and goal alignment

• Experience with Hugging Face, Neo4j, or knowledge graphs
• Background in autonomous decision-making systems
• Background in anomaly detection
• Background in dynamic process optimization
• Track record of publishing, presenting, or open-sourcing agentic AI innovations
• Strong problem-solving aptitude
• Collaborative mindset
• Excellent communication skills
  More Skills
• LLM, agentic AI, multi-agent frameworks, tool calling, API orchestration, ADK, retrieval-augmented generation (RAG), anomaly detection, dynamic process optimization
• Prepare for this role
• Recommended resources to build the skills for this position. Sponsored.
• Top 10 RAG Quick-Prep Questions
• Zenaique
• A shorter RAG interview prep set for quick review.
• Top 50 LangChain Interview Questions
• Zenaique
• Curated LangChain interview questions covering chains, agents, and memory.
• Top 50 RAG Interview Questions
• Zenaique
• Curated RAG interview questions and answers from Zenaique.