Sr. Development Lead (IN)
HCLTech
HCLTech
Opportunity for a skilled Generative AI Engineer passionate about designing, building, and deploying production-grade LLM applications. This role focuses on transforming cutting-edge generative AI advancements into robust and scalable business solutions.
Key areas of specialization include developing advanced Retrieval-Augmented Generation (RAG) pipelines, engineering autonomous agents with reliable tool-calling capabilities, optimizing prompt workflows, exploring parameter-efficient model adaptation techniques like LoRA/QLoRA, and serving high-performance inference APIs through containerized microservices on cloud platforms like AWS or Azure.
Design and implement end-to-end RAG pipelines, including multi-modal document parsing and semantic chunking. Integrate, optimize, and benchmark vector databases for sub-second similarity search. Implement hybrid retrieval strategies combining dense vector embeddings with sparse lexical matching and re-ranking models. Develop stateful multi-agent workflows and autonomous task execution loops. Build robust function-calling and tool-use interfaces connecting LLMs to external systems. Design and test systematic prompt templates using various prompting techniques. Enforce deterministic, validated output structures for reliable downstream data ingestion. Conduct Parameter-Efficient Fine-Tuning (PEFT) on open-weights models for domain-specific tasks. Develop high-throughput asynchronous backend microservices using FastAPI. Implement low-latency streaming inference pipelines. Optimize inference throughput using modern serving engines and containerize applications with Docker for deployment.
Requires a minimum of 3+ years in professional software engineering and applied AI/ML, with at least 1.5+ years of hands-on experience in LLMs and Generative AI. A Bachelor's degree in Computer Science, Software Engineering, Artificial Intelligence, Data Science, or a related technical field is essential. Proficiency in Python with advanced skills in asyncio, type hints, Pydantic, and pytest is expected. Deep familiarity with PyTorch or Hugging Face Transformers is necessary. Extensive hands-on experience with frameworks like LangChain, LangGraph, and LlamaIndex, along with commercial/open foundation model APIs, is crucial. Proven track record building and deploying production RAG architectures using various vector databases is a must. Hands-on proficiency in developing asynchronous REST APIs with FastAPI, Docker containerization, and Git-based workflows is required. Strong analytical problem-solving skills, a solid understanding of transformer architecture, and proactive technical curiosity are core competencies.
HCLTech
IT Consulting