Technical Architect

Job Description

We are looking for a GenAI Architect to design, build, and guide the implementation of Generative AI solutions across enterprise use cases. The role requires strong hands-on and architectural expertise in LLMs, RAG, vector databases, and agentic AI frameworks, along with experience in cloud-native deployments and CI/CD automation. You will collaborate with business stakeholders, data/ML teams, and engineering teams to deliver scalable, secure, and production-ready GenAI platforms and applications.

Key Responsibilities

Architect and design end-to-end GenAI solutions including RAG pipelines, agentic workflows, and multimodal use cases.
Translate business problems into GenAI-driven use cases, solution blueprints, and implementation roadmaps.
Design and implement retrieval systems using embeddings, chunking strategies, metadata filters, reranking, and evaluation metrics.
Select and integrate vector databases and optimize indexing, retrieval performance, and relevance tuning.
Build agentic systems using frameworks such as LangChain, LangGraph, and related orchestration tools.
Define cloud architecture patterns for scalable, secure, and reliable GenAI deployments.
Drive productionization using CI/CD pipelines, containerization using best practices.
Ensure responsible AI practices including security, governance, privacy, compliance, and monitoring.
Provide technical leadership, reviews, mentoring, and best-practice guidance to engineering teams.
Collaborate with product and delivery teams to ensure solution alignment with timelines and business outcomes.

Primary Skills (Must Have)

GenAI / LLM Architecture & Algorithms

Strong knowledge of GenAI algorithms and LLM concepts: prompting, fine-tuning vs RAG, embeddings, context windows, token limits, hallucination control.
Experience designing enterprise GenAI use cases (document Q&A, copilots, summarization, search, workflow automation, customer support, knowledge assistants).
Understanding of evaluation techniques: groundedness, relevance, faithfulness, latency/cost trade-offs.

Vector Databases & Retrieval Systems

Hands-on understanding of vector databases and similarity search concepts:
embeddings, indexing, ANN search, hybrid search, metadata filtering
Experience with tools like Pinecone, FAISS, Weaviate, Chroma, Milvus, Azure AI Search / Elastic (vector) (any relevant combination).

Agentic AI Frameworks

Strong working knowledge of agentic frameworks such as:
LangChain
LangGraph
MCP
Tool calling / function calling, memory, planning, multi-agent workflows, guardrails

Cloud Architecture & Deployments

Experience with cloud services and architecture for GenAI workloads:
compute, networking, storage, IAM/security, logging/monitoring
Knowledge of cloud components supporting AI/ML solutions (managed services preferred).

CI/CD and Productionization

Experience implementing CI/CD pipelines for GenAI apps and services.
Strong understanding of deployment patterns:
containers (Docker), orchestration (Kubernetes), API deployment, model endpoint integration
Familiarity with DevOps/MLOps practices: testing, observability, rollback, scaling, cost controls.

Mandatory Competencies