Senior Technical Lead

• *Job Summary**
• --------------

To designs, build, and deploy production\-grade enterprise applications powered by large language models, retrieval\-augmented generation (RAG) pipelines, and autonomous AI agents.

• *Key Responsibilities**
• -----------------------

Gen AI Architecture: Design and implement RAG systems, multi\-agent workflows, and orchestration frameworks.

LLM Integration: Integrate foundation models (GPT, LLaMA, Claude) with enterprise data lakes, microservices, and external APIs.

Optimization \& MLOps: Fine\-tune models, monitor inference latency, manage vector databases, and control production costs.

Collaboration \& Mentorship: Work with cross\-functional product and data science teams while guiding junior developers

• *Skill Requirements**
• ---------------------

10\-12\+ years of Technical Experience in RPA, GenAI and allied skills.

Programming: Advanced proficiency in Python and backend web frameworks (FastAPI, Flask).

AI Frameworks: Deep hands\-on experience with LangChain, LlamaIndex, and vector databases (Pinecone, Chroma, FAISS).

Cloud \& Infrastructure: Containerization experience using Docker, Kubernetes, and major cloud platforms (AWS, Azure, or GCP).

• *Must Have Skill**
• ------------------

GCP GenAI Engineering,Python,GCP AI \& ML (CCAI/Vertex AI/GenAI),Generative Artificial Intelligence

• *Good to Have Skill**
• ---------------------

Large Language Models (LLMs)

• *Other Requirements**
• ---------------------

Core Programming \& ArchitectureAdvanced Python: Mastery of Python and backend frameworks like FastAPI or Flask to build robust AI services.

Distributed Computing: Experience with PySpark or similar tools for large\-scale data processing pipelines.

System Design: Ability to design microservices, event\-driven architectures, and decoupled, scalable components

Gen AI \& LLM ExpertiseModel Orchestration: Working with major foundation models (GPT, Claude, Gemini, LLaMA) via native SDKs and APIs.

RAG Systems: Designing Retrieval\-Augmented Generation pipelines, context engineering, and vector databases (Pinecone, Weaviate, Chroma).

Agentic Workflows: Building autonomous multi\-agent systems and tool\-calling architectures using frameworks like LangChain, LangGraph, LlamaIndex, or CrewAI.

Fine\-Tuning \& Evaluation: Implementing PEFT, LoRA, and QLoRA, alongside evaluation frameworks like Ragas or DeepEval to measure hallucination and model quality.

MLOps \& Cloud InfrastructureCloud Platforms: Hands\-on deployment using hyperscalers like AWS (Bedrock), Microsoft Azure (Azure OpenAI), or Google Cloud (Vertex AI).

Containerization \& CI/CD: Packaging applications with Docker and Kubernetes, and managing automated deployment pipelines.

Observability: Tracking latency, token costs, LLM tracing, and output performance in production environments.