Generative AI Developer

Job Title: Generative AI Developer

Job Description:

We are seeking a skilled Generative AI Developer with hands-on experience in Large Language Models (LLMs), prompt engineering, and modern GenAI solution design. The ideal candidate should be comfortable working with Retrieval-Augmented Generation (RAG), Agents frameworks, and AWS Bedrock, with a basic understanding of LLMOps practices. Additionally, proficiency in Streamlit for developing quick front-end prototypes of GenAI applications is highly desirable.

The role involves building scalable, real-world GenAI applications and continuously exploring advancements in the field of Generative AI.

Key Responsibilities:

• Develop and maintain GenAI solutions using LLMs, RAG pipelines, and agent-based workflows.
• Integrate LLMs into applications using APIs and cloud-based services like AWS Bedrock.
• Conduct experiments and research on the latest GenAI advancements and implement proof-of-concepts (PoCs).
• Contribute to LLMOps practices including prompt versioning, testing, and basic monitoring.
• Collaborate with architects, data engineers, and DevOps teams to build scalable GenAI solutions.

Technical Requirements:

• 6–8 years of total experience with at least 3+ years of hands-on experience in AI/ML or NLP.
• Hands-on experience working with LLMs (e.g., GPT, Claude, LLaMA, Mistral).
• Understanding of RAG workflows and experience with vector databases (e.g., FAISS, Pinecone, OpenSearch).
• Exposure to agent frameworks like Crewai, LangGraph, Semantic Kernel, or custom orchestrators.
• Familiarity with AWS Bedrock and prompt orchestration through tools like LangChain or PromptLayer.
• Knowledge of basic LLMOps practices such as prompt versioning, monitoring, and logging.
• Proven experience in prompt engineering — designing few-shot examples, controlling hallucinations, and optimizing outputs.
• Proficient in Streamlit for building lightweight, interactive front-ends.
• Strong programming skills in Python and experience with REST APIs.
• Good in Deep Learning architectures: RNN, CNN, Transformer-based models
• Experience with NLP using open-source libraries (e.g., spaCy, Hugging Face, NLTK)
• Familiarity with data storage and search systems such as PostgreSQL, Elasticsearch, or similar.

Preferred Skills:

• Exposure to document processing pipelines and unstructured data extraction.
• Knowledge of MLOps and CI/CD tools (e.g., GitHub Actions, Docker).
• Prior experience integrating GenAI into real-world applications 

Soft Skills:

• Strong analytical and problem-solving skills with the ability to break down complex challenges.
• Curiosity and initiative in researching new GenAI trends and applying them practically.
• Good communication and collaboration skills, especially in a cross-functional team environment.