AI Engineer

Job Summary

We are looking for a hands-on AI Engineer with strong expertise in Generative AI and Agentic AI systems, focused on building and operating production-grade applications.

The ideal candidate must have practical experience designing, developing, and scaling real-world AI solutions powered by LLMs, autonomous agents, and modern AI orchestration frameworks. This role requires strong engineering discipline to deliver reliable, observable, and maintainable AI systems used by real users in production environments.

Responsibilities

• Design, build, and maintain production-grade Generative AI and Agentic AI systems.
• Develop end-to-end LLM-powered applications with strong focus on reliability, scalability, and performance.
• Design and implement autonomous agents with structured reasoning, controlled execution flows, and tool integration.
• Build agent orchestration workflows including memory management, multi-step reasoning, and safe execution mechanisms.
• Implement robust guardrails, monitoring, and observability across agent workflows.
• Develop and optimize retrieval and knowledge augmentation pipelines supporting LLM grounding and contextual accuracy.
• Ensure structured output handling, validation, and predictable system behavior.
• Build scalable serving infrastructure for AI workloads including streaming, caching, and performance optimization.
• Apply LLMOps best practices including evaluation pipelines, prompt management, versioning, and monitoring.
• Optimize cost, latency, and system reliability for production-scale deployments.
• Collaborate with engineering teams to integrate AI systems into production environments following enterprise engineering standards.

Requirements

• 35 years of software or ML engineering experience.
• Proven hands-on experience building and deploying production-grade Generative AI or Agentic AI applications.
• Strong Python expertise with experience building scalable backend services.
• Practical experience with LLM orchestration frameworks such as LangChain, LangGraph, LlamaIndex, or similar.
• Strong understanding of agent architectures, tool calling, memory handling, and workflow orchestration.
• Experience designing and implementing RAG or retrieval-based systems.
• Hands-on experience with multi-agent orchestration patterns.
• Experience fine-tuning or adapting open-source LLMs using modern techniques.
• Experience with LLM evaluation frameworks and observability tools.
• Understanding of AI safety, guardrails, and responsible AI practices.
• Experience working with scalable distributed systems or high-throughput AI services.
• Solid understanding of LLM fundamentals including tokenization, context handling, prompting strategies, and model behavior.
• Experience with vector databases and semantic retrieval systems.
• Experience deploying systems on cloud platforms (AWS / Azure / GCP).
• Hands-on experience with Docker and containerized deployments.
• Strong debugging and problem-solving skills in non-deterministic AI systems.
• Experience operating AI systems in production environments with monitoring and observability.

Technology Stack

• Models: GPT, Claude, Gemini, Mistral, LLaMA
• Frameworks: LangChain, LangGraph, LlamaIndex, Semantic Kernel
• Agent Systems: LangGraph, AutoGen, CrewAI
• Retrieval Storage: Pinecone, Weaviate, Qdrant, pgvector, ChromaDB
• Observability: LangSmith, Langfuse, Arize Phoenix
• Infrastructure: AWS / Azure / GCP, Docker, Kubernetes, FastAPI

Location

Vadodara, Gujarat, India

Job Type

Full time

Disclaimer: This job posting has been aggregated from external source. Role details, content, and availability are subject to change. Applicants are advised to confirm the latest information directly on the company website before applying.