Senior ML/AI Engineer

Senior AI/ML Engineer will primarily be responsible to design, develop, and optimize autonomous AI agents that interact with systems, users, and APIs to perform complex tasks. S/he will work at the intersection of LLMs, agentic frameworks, and cloud architectures, developing self-improving AI workflows for automation, coding, and decision-making.

Responsibilities

• Design, build, and deploy AI agents using LangChain, CrewAI, LangGraph, AutoGen, or similar frameworks
• Integrate large language models (LLMs) (GPT-4,o1, Claude, Llama, Mistral etc.,) into multi-agent systems
• Develop multi-agent orchestration pipelines, enabling collaboration between AI agents for complex task execution
• Knowledge of vector databases and embeddings for retrieval-augmented AI (RAG)
• Implement retrieval-augmented generation (RAG) with vector databases like Milvus, Pinecone, Azure AI Search (with Vector Indexing)
• Optimize AI workflows using Reinforcement Learning (RLHF) and function calling for improved reasoning and automation
• Integrate AI agents with APIs, DevOps tools and existing workflows
• Ensure observability, debugging, and monitoring of AI agent behavior through logging frameworks
• Implement memory persistence for long-term agent interactions using graph-based memory or event stores
• Collaborate with cross-functional teams to embed AI agents into DevOps, automation, and software development processes
• Implement various prompt techniques, including zero-shot, few-shot, chain-of-thought (CoT), and fine-tuning for optimized LLM performance

Qualifications

• B. Tech/B.E. or masters degree in computer science, data science, or a related field
• 8+ years of strong python programming experience with AI/ML frameworks such as TensorFlow, PyTorch
• Experience in building self-improving AI agents for software development (e.g., SWE-bots, or self-improving code generation agents)
• Strong algorithmic thinking, problem-solving skills, and ability to debug AI-driven workflows
• Knowledge of NLP, semantic search, embeddings, and agent memory management
• Ability to work with knowledge graphs and symbolic reasoning techniques
• Familiarity with cloud AI services (Azure AI, AWS Bedrock, Google Vertex AI) and deploying AI agents in Containerized environments like Docker, Kubernetes, AKS or Similar
• Understanding of LLM Ops, including prompt engineering, fine-tuning, retrieval-augmented generation (RAG), and function calling