Search by job, company or skills

Cerebry

Generative AI Engineer

Save
  • Posted 2 months ago
  • Be among the first 50 applicants
Early Applicant

Job Description

About the Role:-

We are seeking a Generative AI Engineer with 2+ years of experience to build and scale production-ready Agentic Systems using Large Language Models (LLMs). You will work on RAG pipelines, agent workflows, evaluation, and deployment of reliable AI systems.

Key Responsibilities:-

-Build retrieval-augmented generation (RAG) pipelines with embeddings, hybrid search, and reranking

-Implement agent orchestration, tool/function calling, and prompt management

-Develop evaluation, monitoring, and observability for LLM systems

-Ensure AI safety, governance, and data privacy best practices

-Optimize performance using caching, batching, and streaming

-Package solutions as APIs/SDKs and deploy using cloud-native tools

Tech Stack:-

-Languages: Python (primary), TypeScript

-Frameworks: FastAPI/Flask, LangChain/LlamaIndex

-LLMs: OpenAI, Anthropic, Google, Azure OpenAI, AWS Bedrock

-Infra: Docker, CI/CD, Terraform/CDK

-Cloud: AWS / Azure / GCP (any one)

Requirements:-

-2+ years of software or AI engineering experience

-Strong Python and backend development skills

-Hands-on experience with LLMs and cloud deployments

-Understanding of scalable systems and data security

What We Offer:-

-Work on cutting-edge Generative AI products

-High ownership and learning opportunities

-Competitive compensation and growth

More Info

Job Type:
Industry:
Employment Type:

About Company

Job ID: 136456609

Similar Jobs

Gurugram, India

Skills:

TensorflowNlpPytorchDockerPythonAWSGcpAzureKubernetesGloVeHugging Facevector databasesMLflowPineconeLLM architectureWord2VecRAG pipelinesChromaDBfine-tuning techniquesAPIs from major AI providersLangChainLLM training methodologiesLoRAQLoRAsentence transformers

Gurugram, Delhi NCR

Skills:

NlpFastAPIAWSDeep LearningMachine LearningHuggingfaceGenerative AI

Gurugram, India

Skills:

TensorflowNlpPytorchPythonLangChainAPIs from major AI providersGloVeGoogleHugging Facevector databasesPineconeLLM training methodologiesLLM architectureWord2VecLoRAOpenAINeural Network fundamentalsRAG pipelinesChromaDBfine-tuning techniquesQLoRAsentence transformers

Delhi, India

Skills:

Node.jsJinja2SqlTypescriptFastAPIPythonLangChainHugging FacePineconeTransformersMilvusLlamaIndex

Gurugram, India, Gurugram

Skills:

Deep LearningMachine LearningAWSCloud ServicesPythonAzureGcpAutoGenNLP LibrariesLang ChainDistributed Computing FrameworksLang GraphOpenAI Assistants API