Sr GenAI Engineer - VectorDBand PostgreSQL (IN)
HCLTech
HCLTech
Drive the creation of cutting-edge AI solutions using large language models and advanced prompt engineering techniques. This role demands deep expertise in Python, RESTful APIs, and various database technologies to architect, build, and refine generative AI applications, ensuring they meet high organizational standards and project goals.
This position is ideal for both individual contributors and those with team leadership experience, focusing primarily on development activities. The role offers flexibility regarding notice periods, prioritizing candidates available within 0-30 days, followed by 30-45 days, and then 45-90 days.
Design and deploy sophisticated LLM-driven solutions using Python frameworks like Flask, Django, and FastAPI, showcasing advanced GenAI and prompt engineering skills.
Develop and integrate RESTful APIs to connect LLM models and vector databases such as Pinecone, PostgreSQL, and Azure AISearch for efficient data retrieval in AI applications.
Enhance the performance and accuracy of generative AI systems by optimizing database schemas and embeddings within PostgreSQL and VectorDB.
Uphold code quality and performance through rigorous code reviews and adherence to best practices in Python, RESTful API development, and prompt engineering.
Lead technical assessments and solution breakdowns, evaluating architectural options and potential risks for GenAI project modules.
Collaborate with stakeholders to establish technical objectives and ensure process compliance throughout the AI-powered solution development lifecycle.
A strong command of GenAI, large language models (LLMs), and prompt engineering is essential. You should possess solid Python programming skills, including experience with frameworks like Flask, Django, and FastAPI.
Proficiency in designing and implementing RESTful APIs for AI integrations is key. Advanced capabilities in database management using PostgreSQL, MySQL, and VectorDB technologies (e.g., Pinecone, Azure AISearch) are required.
A thorough understanding of embedding techniques for generative AI workflows and experience in optimizing code quality, performance, and scalability are expected. A minimum of 6 years of total experience is needed, with at least 5 years specifically in AI/ML technologies.
HCLTech
IT Consulting