Machine Learning Engineer - LLM/RAG

Description :

About the Role :

We are looking for an experienced Machine Learning Engineer specializing in Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), AI Modeling, and MLOps to design, develop, and deploy production-grade AI solutions.

The ideal candidate should have hands-on experience across the complete ML lifecycle - from data preparation and model fine-tuning to deployment, monitoring, and optimization of scalable AI systems on cloud platforms. This role demands strong expertise in generative AI, model optimization, distributed training, cloud-native deployment, and responsible AI practices.

You will work closely with product, engineering, design, and business teams to deliver innovative AI-powered solutions while mentoring junior engineers and driving technical strategy.

Key Responsibilities :

- Design and build enterprise-grade applications powered by Large Language Models (LLMs).

- Develop and optimize Retrieval-Augmented Generation (RAG) pipelines for domain-specific use cases.

- Build AI agents, prompt orchestration frameworks, and multi-step reasoning workflows.

- Implement prompt engineering strategies, prompt templates, and context management.

- Develop guardrails, hallucination detection, moderation pipelines, and AI safety mechanisms.

- Build evaluation frameworks for model performance, prompt effectiveness, and business KPIs.

- Manage the end-to-end ML lifecycle from data collection to production deployment.

- Fine-tune foundation models using techniques such as LoRA, QLoRA, PEFT, and instruction tuning.

- Conduct supervised fine-tuning and experimentation on domain-specific datasets.

- Support advanced training approaches including transfer learning and model adaptation.

- Work with structured, unstructured, and multimodal datasets for training pipelines.

- Deploy scalable AI/ML solutions on AWS cloud infrastructure.

- Build and manage deployments using :

i. AWS SageMaker

ii. Amazon Bedrock

iii. AWS Lambda

iv. EKS / ECS

v. API Gateway

vi. S3 / Glue / Athena

- Build inference APIs and model-serving pipelines for low-latency production environments.

- Implement autoscaling and cost optimization strategies for model serving.

Model Optimization & Performance Engineering :

- Optimize model training and inference performance using :

i. DeepSpeed

ii. Quantization techniques

iii. Mixed precision training

iv. GPU optimization

- Work with GPU clusters and distributed training environments.

- Optimize vector search and embedding pipelines using vector databases.

- Build scalable retrieval pipelines using embeddings and semantic search.

- Work with vector databases such as :

i. Pinecone

ii. Weaviate

iii. Chroma

iv. FAISS

v. Milvus

- Design chunking, indexing, reranking, and retrieval strategies.

- Improve search relevance, latency, and retrieval quality.

- Establish end-to-end MLOps pipelines including CI/CD for ML workflows.

- Implement model versioning, experiment tracking, and monitoring.

- Work with tools such as MLflow, Weights & Biases, or equivalent.

- Set up drift monitoring, alerting, retraining workflows, and performance dashboards.

- Ensure compliance with responsible AI, governance, explainability, and auditability requirements.

- Perform exploratory data analysis (EDA) and feature research for model development.

- Build and maintain ETL/data pipelines for ML training and inference.

- Work with big data frameworks such as Spark or Flink.

- Conduct domain-focused research to improve model performance and business outcomes.

- Collaborate with product managers, UX teams, engineering teams, and stakeholders.

- Translate business requirements into scalable ML/AI solutions.

- Mentor junior engineers and guide technical best practices.

- Drive architecture decisions, code reviews, and deployment standards.

Required Skills & Qualifications :

- 5-12 years of experience in Machine Learning / AI Engineering.

- Minimum 3+ years of experience building and deploying production ML systems.

- 1+ years of hands-on experience with LLMs, RAG systems, and generative AI applications.

- Strong programming skills in Python.

- Hands-on experience with :

i. PyTorch

ii. Hugging Face Transformers

iii. LangChain / LlamaIndex

iv. OpenAI / Anthropic / open-source LLMs

- Strong AWS cloud expertise :

i. SageMaker

ii. Bedrock

iii. Lambda

iv. ECS/EKS

v. S3

- Experience with containerization and orchestration :

i. Docker

ii. Kubernetes

- Strong knowledge of CI/CD pipelines and ML monitoring.

- Experience with vector databases and embedding models.

- Strong understanding of ML system design and production architecture.