Job
Description
Overview - We are hiring experienced AI Developers to lead the design, development, and scaling of intelligent systems using large language models (LLMs). This includes building prompt-based agents, developing and fine-tuning custom AI models, and architecting advanced pipelines across various business functions. You will work across the full AI development lifecycle—from prompt engineering to model training and deployment—while staying at the forefront of innovation in generative AI and autonomous agent frameworks. Key Responsibilities: - Design and deploy intelligent agents using LLMs such as OpenAI GPT-4, Claude, Mistral, Gemini, Cohere, etc. Build prompt-driven and autonomous agents using frameworks like LangChain, AutoGen, CrewAI, Semantic Kernel, LlamaIndex , or custom stacks. Architect and implement multi-agent systems capable of advanced reasoning, coordination, and tool interaction. Incorporate goal-setting, sub-task decomposition, and autonomous feedback loops for agent self-improvement. Develop custom AI models via fine-tuning, supervised learning , or LoRA/QLoRA approaches using Hugging Face Transformers, PyTorch , or TensorFlow . Build and manage Retrieval-Augmented Generation (RAG) pipelines with vector databases like Pinecone, FAISS, Weaviate, or Chroma. Train and evaluate models on custom datasets using modern NLP workflows and distributed training tools. Optimize models for latency, accuracy, and cost efficiency in both prototype and production environments. Create and maintain testing and evaluation pipelines for prompt quality, hallucination detection, and model behavior safety. Integrate external tools, APIs, plugins, and knowledge bases to enhance agent capabilities. Collaborate with product and engineering teams to translate use cases into scalable AI solutions. Required Technical Skills: - 3+ years hands-on experience with large language models, generative AI, conversational systems, or agent-based system development. Proficient in Python , with experience in AI/ML libraries such as Transformers, LangChain, PyTorch, TensorFlow, PEFT , and Scikit-learn. Strong understanding of prompt engineering, instruction tuning , and system prompt architecture. Experience with custom model training, fine-tuning , and deploying models via Hugging Face, OpenAI APIs, or open-source LLMs. Experience designing and implementing RAG pipelines and managing embedding stores. Familiarity with agent orchestration frameworks , tool integration, memory handling, and context management. Working knowledge of containerization (Docker), MLOps , and cloud environments (AWS, GCP, Azure). Preferred Experience: - Exposure to distributed training (DeepSpeed, Accelerate), quantization , or model optimization techniques . Familiarity with LLM evaluation tools (Trulens, LM Eval Harness, custom eval agents). Experience with RLHF, multi-modal models , or voice/chat integrations . Background in data engineering for building high-quality training/evaluation datasets. Experience with self-healing agents, auto-reflection loops, and adaptive control systems . Shift Timing: Night Shift (Fixed timing will be disclosed at the time of joining) Show more Show less
