We are seeking a Senior GenAI & Python Engineer to design, develop, and operationalize production-grade Generative AI capabilities within our enterprise ecosystem. You will work on advanced features such as Retrieval-Augmented Generation (RAG), autonomous agents, conversational AI, and Model Context Protocol (MCP) integrations — ensuring scalability, security, and compliance across all AI deployments.
This is a hands-on engineering role that blends deep Python expertise, LLM framework experience, and secure system design to build enterprise-ready AI solutions.
Key Responsibilities
Core AI Development:
Design and implement LLM-powered solutions including RAG pipelines, chat interfaces, and AI agents.
Develop secure, scalable Python backends and APIs using FastAPI, Flask, or Django.
Integrate with LLM providers (Azure OpenAI, Anthropic, Open Source models) for real-world use cases.
Implement vector databases (Pinecone, Chroma, Weaviate) and semantic search pipelines.
Develop multi-agent frameworks using LangChain, LlamaIndex, LangGraph, Autogen, or Crew.
Optimize performance — including response time, token efficiency, and cost optimization.
Security, Governance & Compliance:
Implement strict input/output validation, PII detection, and content moderation for AI interactions.
Establish robust access control, authentication, and authorization mechanisms.
Build observability systems for model monitoring, audit logging, and responsible AI usage.
Create guardrails to prevent prompt injection and misuse of AI systems.
Ensure enterprise-grade data governance, privacy, and regulatory compliance.
System Architecture & Deployment:
Design modular, scalable architectures for AI workloads in Azure Cloud (preferred) or equivalent cloud platforms.
Containerize applications with Docker and orchestrate using Kubernetes.
Automate deployments using CI/CD pipelines and infrastructure-as-code (Terraform).
Implement caching, batching, and rate-limiting strategies for LLM performance optimization.
Monitor platform health, establish SLAs, and ensure continuous availability.
Collaboration & Knowledge Sharing:
Partner with Fullstack and AI engineers to integrate GenAI APIs into enterprise web apps.
Participate in design and architecture reviews, contributing to best practices and standards.
Stay current with emerging research, frameworks, and interoperability protocols (MCP, A2A).
Mentor junior engineers and contribute to internal knowledge-sharing sessions.
Required Qualifications:
Technical Expertise:
Python Development: 3+ years of experience in backend or systems programming.
LLM Frameworks: Hands-on experience with LangChain, LlamaIndex, LangGraph, Crew, Autogen, or similar.
API Development: Proven track record building RESTful APIs (FastAPI, Flask, Django).
Vector Databases: Proficiency in Pinecone, Weaviate, Chroma, or other embedding stores.
Cloud Platforms: Azure (preferred), AWS, or GCP with IaC (Terraform, Bicep) exposure.
Containerization & CI/CD: Strong knowledge of Docker, Kubernetes, and automation workflows.
AI & Data Knowledge:
Deep understanding of LLM capabilities, limitations, and prompt engineering.
Experience implementing RAG architectures (chunking, embedding, and retrieval strategies).
Familiarity with LLM evaluation frameworks (TruLens, Helicone, PromptLayer).
Understanding of agent orchestration and tool-execution patterns.
Awareness of Model Context Protocol (MCP) or Agent2Agent (A2A) interoperability.
Security & Infrastructure:
Strong grasp of enterprise authentication protocols (OAuth, SAML, JWT).
Experience with PostgreSQL, MongoDB, or Redis for data persistence.
Knowledge of compliance standards, audit logging, and secure data handling.
Soft Skills:
Excellent problem-solving and debugging skills.
Strong communication and teamwork across AI, DevOps, and product teams.
A proactive, research-driven mindset with a focus on delivering reliable, scalable AI systems.
Success Metrics:
Reduction in response latency and token cost per request.
Stability and uptime of deployed GenAI systems.
Compliance adherence (security, privacy, audit readiness).
Adoption of AI features across internal business units.
Python Development, Backend Development, Systems Programming, LLM Frameworks, LangChain, LlamaIndex, LangGraph, Crew, Autogen, API Development, RESTful APIs, FastAPI, Flask, Django, Vector Databases, Pinecone, Weaviate, Chroma, Embedding Stores, Azure Cloud, AWS, GCP, Terraform, Bicep, Docker, Kubernetes, CI/CD, Automation Workflows, LLM Capabilities, Prompt Engineering, RAG Architectures, Chunking, Embedding, Retrieval Strategies, LLM Evaluation Frameworks, TruLens, Helicone, PromptLayer, Agent Orchestration, Tool Execution Patterns, Model Context Protocol, MCP, Agent2Agent, A2A, OAuth, SAML, JWT, PostgreSQL, MongoDB, Redis, Compliance Standards, Audit Logging, Secure Data Handling, Problem Solving, Debugging, Communication, Teamwork, Research-driven Mindset, Scalable AI Systems