ExponentialAI - Senior AI Engineer - LLM/RAG

Key Responsibilities :

- Build and deploy AI/ML applications using LLMs and traditional ML models

- Design and implement RAG pipelines, semantic search, embeddings, and vector database integrations

- Develop scalable backend services and APIs for AI products

- Build microservices for model serving, inference orchestration, and workflow automation

- Design feature engineering pipelines, data preprocessing, and model training systems

- Implement MLOps practices including CI/CD, model monitoring, drift detection, and automated retraining

- Build observability for AI systems including latency, usage, and quality monitoring

- Deploy AI workloads using cloud-native tools and container orchestration

- Collaborate with product, engineering, and data teams to ship AI features into production

Required Skills :

AI / ML / GenAI :

- Experience with LLM application development

- Strong knowledge of RAG, embeddings, prompt engineering, and fine-tuning

- Hands-on experience with :

1. LangChain

2. LlamaIndex

3. Hugging Face

- Experience with vector databases :

1. FAISS

2. Pinecone

3. Chroma

- Knowledge of model optimization :

1. LoRA

2. QLoRA

3. quantization

4. vLLM

Backend Engineering :

- Hands-on with :

1. FastAPI

2. Flask

- REST API design

- Microservices architecture

- Distributed systems fundamentals

- Async programming

- Caching and queue systems

- Database design and optimization

- API security and authentication

- Production debugging and monitoring

Data & Infrastructure :

- SQL and NoSQL databases

- ETL pipelines

- Streaming and batch processing

- Hands-on with :

1. Apache Kafka

2. RabbitMQ

3. Dask

MLOps / Deployment :

- Experience with :

1. MLflow

2. Kubeflow

3. Amazon SageMaker

4. Azure Machine Learning

- CI/CD pipelines

- Model monitoring

- A/B testing

- Experiment tracking

- Dockerized deployments

Cloud & DevOps :

- Experience with :

1. Amazon Web Services

2. Microsoft Azure

3. Google Cloud

- Hands-on with :

1. Docker

2. Kubernetes

- Production deployment and scaling

Preferred :

- Experience in end-to-end AI product development

- Knowledge of knowledge graphs and NLP pipelines

- Experience with model governance and responsible AI

- Strong system design and architecture skills

- Experience building customer-facing AI applications

- Ability to independently own and drive technical initiatives