Senior Developer (DPO) (IN)
HCLTech
HCLTech
We are looking for a highly skilled Generative AI Engineer with a strong software engineering background and at least 3 years of professional experience in applied AI/ML. This role focuses on designing, building, and deploying production-ready LLM applications, translating cutting-edge generative AI advancements into robust and scalable business solutions.
You will specialize in developing advanced Retrieval-Augmented Generation (RAG) pipelines, creating autonomous agents with reliable tool-calling capabilities, fine-tuning prompt workflows, experimenting with efficient model adaptation techniques (like LoRA/QLoRA), and serving high-performance inference APIs through containerized microservices on cloud platforms such as AWS or Microsoft Azure.
Key responsibilities include architecting and engineering RAG pipelines with advanced features like multi-modal document parsing and semantic chunking. You will manage and optimize vector databases for sub-second similarity searches and implement hybrid retrieval strategies combining vector embeddings with keyword matching. Additionally, you will develop sophisticated agentic workflows using frameworks like LangChain and LangGraph, build robust function-calling interfaces to connect LLMs with external systems, and implement error-handling to prevent infinite agent loops.
Further duties involve advanced prompt engineering using techniques like Chain-of-Thought, ensuring structured and validated outputs with tools like Pydantic, and conducting parameter-efficient fine-tuning (PEFT) on open-weight models. You will develop high-throughput asynchronous backend microservices using FastAPI, optimize streaming inference latency, and deploy containerized applications on cloud platforms using Docker and Kubernetes. Implementing automated model evaluation, enterprise-grade AI guardrails, and comprehensive LLMOps observability for tracing and cost monitoring are also core aspects of this role.
Candidates should possess a minimum of 3 years of professional software engineering or data science experience, with at least 1.5 years specifically focused on Generative AI/LLM development. A Bachelor’s degree in Computer Science, Software Engineering, Artificial Intelligence, Data Science, or a related technical field is required. Advanced Python programming skills, including asyncio, type hints, Pydantic, and pytest, along with deep familiarity with PyTorch or Hugging Face Transformers, are essential.
Extensive hands-on experience with GenAI frameworks such as LangChain, LangGraph, and LlamaIndex, as well as commercial and open foundation model APIs (OpenAI, Anthropic, Bedrock), is crucial. Proven experience in building and deploying production RAG architectures using vector databases (Pinecone, Chroma, Qdrant, pgvector) is necessary. Proficiency in developing asynchronous REST APIs with FastAPI, Docker containerization, and Git-based workflows is also required. Strong analytical problem-solving skills, a solid understanding of transformer architectures, and a proactive curiosity for new technologies are core competencies.
HCLTech
IT Consulting