Senior Solution Architect (AI / LLM solutions)

ZF; Hyderabad; On-site; INR 4,000,000 - 7,000,000; Full time

Job summary

ZF in Hyderabad seeks senior architects to translate complex automotive and engineering challenges into scalable AI, cloud, and software architectures. You will drive solutions from research to production across global teams.

Responsibilities include owning the enterprise GenAI/Agentic AI architecture, guiding platform patterns, and balancing quality, cost and security while leveraging LangGraph, LangChain and leading cloud platforms.

Qualifications

• Bachelor's or master's degree in computer science, engineering, AI or a related field.
• 10+ years in software, data or ML engineering with at least 3 years as lead architect.
• Produced 23+ production GenAI/LLM solutions with end-to-end architecture ownership.
• Hands-on agentic systems with tool use, state management and human-in-the-loop controls.
• Experience with LangGraph / LangChain or managed platforms like AWS Bedrock / Azure Foundry.

Responsibilities

• Own the technical architecture of enterprise Generative AI and Agentic AI solutions from framing to production.
• Translate complex automotive challenges into scalable AI, cloud and software architecture.
• Set reference architecture, platform patterns and guardrails for multiple teams.
• Lead make-or-buy decisions, model selection and customization approaches balancing quality and cost.
• Design multi-agent systems on leading frameworks and cloud platforms, ensuring security and observability.

Skills

LLM / Generative AI

Architectural leadership

Python

API engineering

Cloud platforms

LangGraph / LangChain

Security and compliance

Education

Bachelor's or Master's in CS/Engineering/AI

Tools

LangGraph

LangChain

AWS Bedrock

Azure AI Foundry

Job description

Job Summary

Our team builds enterprise-grade AI platforms and solutions across Agentic AI, Generative AI for the software development lifecycle, systems engineering, automated testing, MLOps, computer vision, and engineering data intelligence.

We are looking for architects who can translate complex automotive and engineering challenges into scalable AI, cloud, and software architecture, and help take solutions from research and proof of concept to production across global engineering teams.

Responsibilities

• End-to-end ownership: You'll own the technical architecture of enterprise Generative AI and Agentic AI solutions, from framing the business problem through to secure, observable and cost-efficient production systems.
• Real-world impact: You'll turn LLM capabilities into reliable, auditable solutions that hold up against complex enterprise data, strict security and compliance requirements, tight latency and cost budgets, and unpredictable model behavior. This role goes well beyond proof of concept.
• Architecture leadership: You'll set the reference architecture, platform patterns and guardrails that multiple engineering teams build on.
• Strategic decisions: You'll lead decisions on what to build versus buy, which models to use, and whether to customize models through fine-tuning, weighing quality, cost, scalability and vendor independence.
• Cutting-edge technology: You'll design multi-agent systems on leading frameworks and cloud platforms, such as LangGraph, AWS Bedrock and Azure AI Foundry.
• Visibility and influence: You'll be the trusted technical authority for business leaders, security teams and enterprise architecture boards.

Requirements

• A bachelors or masters degree in computer science, Engineering, AI or a related field.
• 10+ years in software, data or ML engineering, including at least 3 years as a solution or lead architect.
• Production GenAI delivery: You have delivered at least 23 LLM / Generative AI solutions into production, not only proofs of concept, and owned the architecture and non-functional requirements end to end.
• Agentic AI: You have built hands‑on agentic systems hands‑on, with tool use, state management and human-in-the-loop controls. You've used code‑first frameworks such as LangGraph / LangChain or managed platforms such as AWS Bedrock Agents or Azure AI Foundry Agent Service.
• LLM and model expertise: You have a strong grasp of LLM fundamentals (transformers, embeddings, context windows). You have hands‑on experience customising models through fine‑tuning (e.g., LoRA / QLoRA) and evaluating them, and you can choose sensibly between prompting, RAG and training.
• Engineering and cloud: You are an expert in Python and API enginee0ring (FastAPI, async, event-driven design). You have strong architecture experience on at least one hyperscaler (AWS, Azure or GCP), including networking, identity and security.
• RAG, quality and security: You have practical experience with vector databases, hybrid search and retrieval evaluation. You've implemented LLM evaluation, tracing and observability in production, and you're well-grounded in AI security (prompt-injection defence, data protection).