AI Engineer

Keka Inc.; Bengaluru; On-site; INR 1,200,000 - 1,800,000; Full time

Job summary

Keka Inc. seeks a seasoned AI Engineer to design, fine-tune, and deploy scalable AI systems at scale. You will work at the intersection of LLMs, ML, and software engineering—developing production-ready AI features and pipelines that power our core product.

Design, implement, and optimize AI/ML models, RAG architectures, and embedding pipelines; collaborate with product and backend teams to ship robust AI capabilities. Strong Python and ML library expertise required.

Qualifications

• Strong Python programming and AI/ML fundamentals.
• Hands-on with LLM APIs and prompt engineering.
• Experience in RAG systems and embedding models.
• Familiar with LangChain, LlamaIndex, AutoGen, CrewAI, or Semantic Kernel.
• Cloud deployment experience (AWS SageMaker, GCP Vertex AI, Azure ML).
• Proficiency with MLOps tools.

Responsibilities

• Design, develop, and deploy AI/ML models and pipelines in production environments.
• Implement RAG architectures and agentic AI workflows.
• Fine-tune and optimize LLMs for domain-specific use cases using RLHF, LoRA, QLoRA.
• Build robust prompt engineering frameworks and evaluation pipelines.
• Integrate LLM APIs and open-source models into product features.
• Develop and maintain vector search infrastructure and embedding pipelines.
• Collaborate with architects, backend engineers, and product teams on AI feature delivery.
• Monitor model performance, conduct A/B testing, and iterate based on metrics.
• Implement guardrails, safety layers, and hallucination-mitigation strategies.
• Contribute to MLOps practices: model versioning, deployment pipelines, monitoring.

Skills

Python proficiency

PyTorch

TensorFlow

Transformers

LLM APIs

Prompt engineering

RAG systems

Embedding models

LangChain

MLOps

Tools

Docker

Kubernetes

MLflow

Weights & Biases

DVC

SageMaker

Job description

We are seeking a seasoned AI Engineer to build, fine-tune, and deploy intelligent AI systems at scale. You will

work at the intersection of LLMs, machine learning, and software engineering — developing production-ready AI

features and pipelines that power our core product.

KEY RESPONSIBILITIES

• Design, develop, and deploy AI/ML models and pipelines in production environments
• Implement Retrieval-Augmented Generation (RAG) architectures and agentic AI workflows
• Fine-tune and optimize LLMs for domain-specific use cases using RLHF, LoRA, QLoRA
• Build robust prompt engineering frameworks and evaluation pipelines
• Integrate LLM APIs (OpenAI, Claude, Gemini) and open-source models into product features
• Develop and maintain vector search infrastructure and embedding pipelines
• Collaborate with architects, backend engineers, and product teams on AI feature delivery
• Monitor model performance, conduct A/B testing, and iterate based on metrics
• Implement guardrails, safety layers, and hallucination-mitigation strategies
• Contribute to MLOps practices: model versioning, deployment pipelines, monitoring

KEY SKILLS & REQUIREMENTS

• Strong expertise in Python, with deep knowledge of AI/ML libraries (PyTorch, TensorFlow, HuggingFace Transformers)
• Hands-on experience with LLM APIs and prompt engineering techniques (CoT, few-shot, ReAct)
• Experience with RAG systems, embedding models (text-embedding-3, BGE, Cohere), and vector stores
• Knowledge of agentic frameworks: LangChain, LlamaIndex, AutoGen, CrewAI, or Semantic Kernel
• Familiarity with fine-tuning techniques: LoRA, QLoRA, PEFT, instruction tuning
• Experience deploying models on cloud platforms (AWS SageMaker, GCP Vertex AI, Azure ML)
• Understanding of data preprocessing, feature engineering, and model evaluation metrics
• Proficiency with MLOps tools: MLflow, DVC, Weights & Biases, BentoML
• Experience with containerization and orchestration: Docker, Kubernetes
• Strong debugging and experimentation skills with Jupyter, FastAPI, Streamlit

NICE TO HAVE

• Experience with multi-modal models (vision-language models, Whisper, DALL-E)
• Published papers or Kaggle/competition achievements
• Exposure to speech AI, computer vision, or NLP specializations
• Knowledge of responsible AI, fairness metrics, and bias