Technical Architect

Job Description

We are looking for a GenAI Architect to design and scale enterprise Generative AI solutions. This role requires strong hands-on and architectural expertise in LLMs, RAG systems, vector databases, and agentic AI frameworks, along with experience deploying production-grade GenAI platforms on the cloud.

Key Responsibilities:
•    Design end-to-end GenAI architectures including RAG pipelines, agent workflows, and multimodal use cases.
•    Translate business needs into GenAI use cases, architecture designs, and implementation roadmaps.
•    Architect and optimize retrieval systems (embeddings, chunking, metadata filtering, reranking, evaluations).
•    Select and integrate vector databases, tuning for performance, relevance, and scalability.
•    Build agentic AI solutions using LangChain, LangGraph, MCP, and tool-calling frameworks.
•    Define cloud-native architectures for secure, scalable GenAI deployments.
•    Drive productionization using CI/CD pipelines, containers, observability, and cost controls.
•    Ensure Responsible AI practices covering security, privacy, compliance, and monitoring.
•    Provide technical leadership and mentoring across engineering teams.

Required Skills:
GenAI & LLM Architecture
•    Strong understanding of LLMs: prompting, RAG vs fine-tuning, embeddings, context limits, hallucination control.
•    Experience delivering enterprise GenAI solutions (copilots, document Q&A, summarization, assistants).
•    Knowledge of evaluation metrics: relevance, groundedness, latency, and cost.
Retrieval & Vector Databases
•    Experience with embeddings, ANN search, hybrid retrieval, and metadata filtering.
•    Hands-on exposure to vector stores such as Pinecone, FAISS, Weaviate, Chroma, Milvus, Azure AI Search, Elastic.
Agentic AI
•    Working knowledge of LangChain, LangGraph, MCP, multi-agent workflows, memory, and guardrails.
Cloud & DevOps
•    Experience designing GenAI workloads on AWS / Azure / GCP.
•    Strong understanding of Docker, Kubernetes, API deployments, CI/CD, and MLOps practices.

Good to Have
•    RAG optimization (advanced chunking, reranking, feedback loops).
•    LLM integrations (OpenAI, Azure OpenAI, Anthropic, Gemini, open-source models).
•    GenAI observability, prompt/version management, and Responsible AI controls.

Mandatory Competencies