Straive - Generative AI Engineer - LLM/RAG

About the Role :

We are looking for a highly skilled and innovative Generative AI Engineer LLM/RAG to design, develop, and deploy cutting-edge AI applications powered by Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) architectures.

The ideal candidate will have hands-on experience building scalable GenAI systems, integrating enterprise data sources, developing intelligent AI agents, and optimizing LLM performance for production-grade applications.

This role requires strong expertise in NLP, prompt engineering, vector databases, model orchestration frameworks, and AI infrastructure.

You will collaborate closely with product, engineering, and business teams to build AI-powered solutions that improve automation, search, knowledge management, customer experience, and operational efficiency.

Key Responsibilities :

- Design, build, and deploy applications powered by Large Language Models (LLMs).

- Fine-tune, evaluate, and optimize LLMs for domain-specific use cases.

- Design and implement scalable RAG pipelines integrating structured and unstructured enterprise data.

- Build semantic search and retrieval systems using vector embeddings and vector databases.

- Develop document ingestion, chunking, embedding, indexing, retrieval, and response-generation pipelines.

- Optimize retrieval accuracy, latency, context handling, and hallucination reduction.

- Develop advanced prompt engineering strategies for high-quality AI outputs.

- Build multi-step AI workflows and agent-based architectures.

- Implement guardrails, evaluation frameworks, and prompt optimization techniques.

- Build scalable data pipelines for document processing, embedding generation, and knowledge retrieval.

- Work with multiple data formats including PDFs, APIs, databases, websites, and enterprise systems.

- Develop preprocessing pipelines for text cleaning, metadata extraction, and semantic indexing.

- Deploy GenAI applications into production environments with scalability and monitoring.

- Build APIs and microservices for AI model integration.

- Implement CI/CD pipelines, model monitoring, logging, and observability frameworks.

- Optimize infrastructure for cost, latency, throughput, and reliability.

- Evaluate LLM outputs for relevance, factual accuracy, safety, and consistency.

- Implement automated testing and benchmarking frameworks for GenAI applications.

- Monitor model drift, prompt degradation, and retrieval effectiveness.

- Work closely with product managers, data scientists, software engineers, and business stakeholders.

- Translate business requirements into scalable AI solutions.

- Provide technical guidance and mentorship to junior engineers where required.

Required Skills & Technical Expertise :

Programming & Development :

- Python

- REST APIs

- Microservices architecture

- FastAPI / Flask

- Async programming

- Backend integration

Generative AI & LLM Technologies :

- Hugging Face Transformers

- Open-source LLMs

- Strong understanding of :

i. Transformer architecture

ii. Tokenization

iii. Embeddings

iv. Fine-tuning

v. Prompt engineering

vi. Context management

RAG & Vector Databases :

- Experience building RAG systems using :

i. LangChain

ii. LlamaIndex

iii. Haystack

- Hands-on experience with vector databases such as :

i. Pinecone

ii. Weaviate

iii. ChromaDB

iv. FAISS

v. Milvus

Cloud & Infrastructure :

- Experience with cloud platforms :

i. AWS

ii. Azure

iii. GCP

- Familiarity with :

i. Docker

ii. Kubernetes

iii. CI/CD pipelines

iv. Serverless architectures

Databases & Search :

- Strong understanding of :

i. SQL/NoSQL databases

ii. Elasticsearch/OpenSearch

iii. Semantic search systems

MLOps & Monitoring :