Straive - Senior Generative AI Developer - RAG/LLM

Job Description :

Straive is looking for a Senior GenAI Developer with a strong software engineering background and handson expertise in Generative AI, Large Language Models (LLMs), RetrievalAugmented Generation (RAG), prompt engineering, and cloudnative application development. The ideal candidate will be responsible for designing, developing, optimizing, and deploying productiongrade GenAI solutions for enterprise use cases. You will work closely with engineering, product, and business teams to translate complex requirements into scalable AIpowered applications. The role requires strong expertise in Python and modern AI/ML frameworks, along with experience building reliable, secure, and highperformance LLM applications.

Key Responsibilities :

- Design and architect scalable Generative AI applications using LLMs and modern AI frameworks.

- Build and optimize RetrievalAugmented Generation (RAG) pipelines for enterprise applications.

- Develop document ingestion, preprocessing, chunking, embedding, retrieval, reranking, and responsegeneration workflows.

- Implement advanced Prompt Engineering techniques, including fewshot prompting, structured prompting, prompt chaining, and reasoningbased approaches.

- Integrate commercial and opensource LLMs such as OpenAI, Anthropic, Llama, and Mistral into enterprise applications.

- Develop and implement LLM finetuning solutions using LoRA/QLoRA and evaluate model performance.

- Work with vector databases such as Pinecone, ChromaDB, or equivalent technologies.

- Build robust APIs and backend services using Python, RESTful APIs, and/or GraphQL.

- Optimize GenAI applications for latency, scalability, accuracy, reliability, and cost efficiency.

- Develop evaluation frameworks to measure LLM response quality, relevance, hallucination, latency, and retrieval performance.

- Implement techniques to improve RAG accuracy, including metadata filtering, hybrid search, reranking, query transformation, and contextual retrieval.

- Deploy AI applications using cloud platforms such as AWS, Azure, or GCP.

- Containerize applications using Docker and deploy/manage workloads using Kubernetes.

- Implement CI/CD pipelines and follow DevOps best practices for production deployments.

- Ensure enterprise applications follow appropriate security, privacy, governance, and accesscontrol practices.

- Troubleshoot production issues and continuously improve application performance.

- Conduct code reviews and establish software engineering best practices.

- Mentor junior developers and contribute to technical design discussions and architecture decisions.

- Stay updated with emerging developments in LLMs, GenAI frameworks, agentic AI, RAG, model optimization, and AI infrastructure.

Required Technical Skills :

Generative AI & LLM :

- Strong handson experience with Generative AI and Large Language Models.

- Experience working with OpenAI, Anthropic, Llama, Mistral, or similar models.

- Strong understanding of LLM architecture, inference, context windows, embeddings, tokenization, and model limitations.

- Experience with RAG architecture and pipeline optimization.

- Strong knowledge of prompt engineering and LLM application design.

- Experience with LangChain and/or LlamaIndex.

RAG & Vector Databases :

- Handson experience building endtoend RAG solutions.

- Experience with Pinecone, ChromaDB, FAISS, Weaviate, Milvus, or equivalent vector databases.

- Understanding of embeddings, semantic search, similarity search, hybrid search, metadata filtering, and reranking.

- Experience optimizing retrieval quality and reducing hallucinations.

Model FineTuning :

- Practical experience with LoRA/QLoRA or similar parameterefficient finetuning techniques.

- Experience preparing datasets for model finetuning.

- Knowledge of model evaluation, benchmarking, and performance optimization.

- Experience working with opensource LLMs is highly desirable.

Software Engineering :

- Expertlevel Python programming skills.

- Strong understanding of OOP, design patterns, data structures, and algorithms.

- Experience developing scalable backend applications.

- Strong knowledge of RESTful APIs and/or GraphQL.

- Experience with Git and modern software development practices.

- Ability to write clean, maintainable, testable, and productionready code.

Cloud & DevOps :

- Handson experience with at least one major cloud platform: AWS Microsoft Azure Google Cloud Platform (GCP).

- Experience with Docker and Kubernetes.

- Understanding of CI/CD pipelines and automated deployment.

- Familiarity with cloudbased AI/ML services and infrastructure.

- Experience monitoring and troubleshooting production applications.

Preferred / Good-to-Have Skills :

- Experience building AI Agents / Agentic AI workflows.

- Familiarity with tools such as LangGraph, Semantic Kernel, AutoGen, or similar agent frameworks.

- Experience with multimodal AI, including text, image, or document processing.

- Knowledge of MLflow, Hugging Face, PyTorch, or TensorFlow.

- Experience with observability and monitoring of LLM applications.

- Understanding of responsible AI, AI governance, data privacy, and security.

- Experience working with enterprisescale AI applications.

- Familiarity with SQL and NoSQL databases.

- Experience working in Agile/Scrum development environments.

Qualifications :

- Bachelor's or Master's degree in Computer Science, Information Technology, Artificial Intelligence, Data Science, Engineering, or a related discipline.

- 6 - 10 years of overall software development experience, with significant handson experience in GenAI/LLM application development.

- Strong experience taking AI solutions from POC/prototype to production.

- Excellent problemsolving, communication, collaboration, and mentoring skills.