Python Developer - Gen AI

About the Company:

Everest DX – We are a Digital Platform Services company, headquartered in Stamford. Our Platform/Solution includes Orchestration, Intelligent operations with BOTs’, AI-powered analytics for Enterprise IT. Our vision is to enable Digital Transformation for enterprises to deliver seamless customer experience, business efficiency and actionable insights through an integrated set of futuristic digital technologies.

Digital Transformation Services - Specialized in Design, Build, Develop, Integrate, and Manage cloud solutions and modernize Data centers, build a Cloud-native application and migrate existing applications into secure, multi-cloud environments to support digital transformation. Our Digital

Platform Services enable organizations to reduce IT resource requirements and improve productivity, in addition to lowering costs and speeding digital transformation.

Digital Platform - Cloud Intelligent Management (CiM) - An Autonomous Hybrid Cloud Management Platform that works across multi-cloud environments. helps enterprise Digital Transformation get most out of the cloud strategy while reducing Cost, Risk and Speed.

To know more please visit: http://www.everestdx.com

Job Title

Job Location

Job Type

Experience

Notice Period - Immediate to 15 days joiners are highly preferred

Key Responsibilities:

1. Application Development

• Design and develop GenAI-enabled microservices and APIs using Python (FastAPI, Flask, Django).
• Implement LLM integrations using frameworks such as LangChain, LlamaIndex, Semantic Kernel, or CrewAI.
• Build and manage RAG pipelines combining embeddings, vector stores, and retrieval mechanisms.
• Develop prompt templates and implement prompt chaining/orchestration for conversational AI systems.

2. Model & Data Integration

• Integrate models via APIs from OpenAI, Anthropic, Azure OpenAI, AWS Bedrock, or Hugging Face.
• Preprocess and vectorize text data using transformers, sentence embeddings, or custom tokenizers.
• Work with vector databases such as Pinecone, FAISS, Milvus, Weaviate, or Amazon OpenSearch.
• Collaborate with data engineers to connect structured and unstructured datasets (S3, Cosmos DB, SQL, etc.).

3. Cloud & Deployment

• Containerize GenAI services using Docker and deploy on Kubernetes (EKS/AKS).
• Automate deployment pipelines using GitHub Actions, Azure DevOps, or Terraform.
• Implement logging, monitoring, and model telemetry using CloudWatch, Application Insights, or Prometheus.
• Ensure secure API management and key handling via AWS Secrets Manager or Azure Key Vault.

4. Optimization & Scalability

• Optimize inference latency and cost for LLM-based applications.
• Implement caching, batching, and token management strategies.
• Fine-tune or adapt models for domain-specific applications.
• Apply AI guardrails and output moderation for responsible AI use.

Required Skills & Qualifications

Core Technical Skills

Strong expertise in Python (6+ years) with knowledge of:

• Async programming, REST APIs, and design patterns.
• Libraries: FastAPI, Flask, Pydantic, SQLAlchemy, Pandas, NumPy.

Proficiency in AI/GenAI SDKs and APIs:

• OpenAI / Azure OpenAI / AWS Bedrock / Hugging Face Transformers.

Familiarity with LLM orchestration:

• LangChain, LlamaIndex, Semantic Kernel, CrewAI, or Dust.

Understanding of embeddings, vector databases, and RAG workflows.

Cloud & DevOps Skills

Strong hands-on experience in AWS or Azure:

• AWS: Lambda, ECS/EKS, S3, SageMaker, Bedrock.
• Azure: Azure OpenAI, Azure ML, Cognitive Services, AKS.

Experience with CI/CD, IaC (Terraform/Bicep), and API gateways.

Knowledge of containerization and cloud security best practices.

AI & ML Fundamentals

Good understanding of:

• NLP, embeddings, and tokenization.
• Prompt engineering and few-shot learning techniques.
• Model performance metrics (latency, perplexity, accuracy).