Lead AI Engineer

FINVASIA CAREER; Nagar; On-site; INR 1,500,000 - 2,100,000; Full time

Job summary

Keka Technologies Private Limited is seeking a Senior AI Architect to lead design, development, and deployment of AI/ML and Generative AI solutions across business and product use cases.

You will define technical strategy, standards, and roadmaps; architect LLM-powered applications and AI agents; and build scalable AI systems with governance, security, and observability. Collaboration with product and engineering teams is essential.

Qualifications

• Strong proficiency in Python and AI/ML frameworks.
• Hands-on experience with Generative AI, LLMs, NLP, ML and DL.
• Understanding of RAG, embeddings, vector databases and prompt engineering.
• Experience with AI agents, orchestration, guardrails, and human-in-the-loop systems.
• Knowledge of REST APIs, microservices, cloud architectures and MLOps/LLMOps.

Responsibilities

• Lead the design, development, and deployment of AI/ML and Generative AI solutions for business and product use cases.
• Define AI technical strategy, architecture standards, engineering practices, and technology roadmaps.
• Architect and build LLM-powered applications, AI agents, and RAG systems.
• Design and implement context engineering approaches for AI systems.
• Design AI harnesses with orchestration, guardrails, validation, observability, and human-in-the-loop workflows.
• Evaluate models from major platforms and select based on capability, cost, latency, and security.
• Develop and optimize prompts, embeddings, vector search, fine-tuning, and inference strategies.
• Build scalable AI architectures using Python, APIs, microservices, and cloud infra.
• Create production-grade AI/ML pipelines and establish evaluation frameworks.
• Mentor AI/ML engineers and contribute to hiring and standards.
• Collaborate with PMs and engineers to translate business requirements into scalable AI solutions.
• Monitor AI system performance and continuously improve production systems.

Skills

Python

Generative AI

LLMs

NLP

RAG

Embeddings

Vector databases

REST APIs

Microservices

Cloud architectures

Docker

Kubernetes

MLOps

AI security

Tools

LangChain

LlamaIndex

PyTorch

TensorFlow

Pinecone

Weaviate

Job description

• Lead the design, development, and deployment of AI/ML and Generative AI solutions for business and product use cases.
• Define AI technical strategy, architecture standards, engineering practices, and technology roadmaps across product initiatives.
• Architect and build LLM-powered applications, AI agents, agentic workflows, RAG systems, intelligent automation, and AI-powered decision-support systems.
• Design and implement context engineering approaches to provide AI systems with the right information, tools, memory, instructions, and constraints at the right time.
• Design and build reliable AI harnesses around models, including orchestration, tool use, guardrails, validation, observability, fallback mechanisms, and human-in-the-loop workflows.
• Evaluate and implement models from OpenAI, Anthropic, Google, Meta, Hugging Face, and other AI platforms based on capability, performance, cost, latency, security, and business requirements.
• Develop and optimize prompt and context engineering, embeddings, vector search, fine-tuning, model selection, and inference strategies.
• Design scalable AI architectures using Python, APIs, microservices, distributed systems, and cloud infrastructure.
• Build production-grade AI/ML pipelines covering data preparation, experimentation, evaluation, testing, deployment, monitoring, and optimization.
• Establish LLM and agent evaluation frameworks covering quality, accuracy, hallucination, safety, latency, cost, reliability, and task completion.
• Build automated evaluation and regression-testing mechanisms for AI applications and continuously improve model and system performance using production feedback.
• Lead the integration of AI solutions with existing applications, APIs, databases, enterprise systems, and product workflows.
• Work with engineering teams to deploy AI systems using AWS/Azure/GCP and modern MLOps/LLMOps practices.
• Establish standards for AI security, data privacy, model governance, responsible AI, prompt-injection protection, access control, and AI application observability.
• Design mechanisms for AI system reliability, including validation, guardrails, failure handling, fallback strategies, and controlled model behavior.
• Conduct POCs and technical research on emerging AI technologies and identify opportunities for their application within the business.
• Identify and evaluate opportunities for AI across areas such as financial intelligence, customer experience, personalization, fraud and risk, compliance, financial-document intelligence, trading and investment workflows, and business automation.
• Mentor and guide AI/ML engineers and contribute to technical hiring, capability development, and engineering standards.
• Collaborate with Product Managers, engineering teams, and business stakeholders to convert business requirements into scalable and measurable AI solutions.
• Monitor AI system performance, accuracy, latency, cost, reliability, and business outcomes and continuously improve production systems.
• Drive AI initiatives from POC to production, ensuring measurable business value and engineering quality.

Required Technical Skills

• Strong proficiency in Python and AI/ML frameworks.
• Hands-on experience with Generative AI, LLMs, NLP, Machine Learning, and Deep Learning.
• Strong understanding of RAG, embeddings, vector databases, prompt engineering, context engineering, function/tool calling, and AI agents.
• Experience designing agentic workflows, AI orchestration, AI harnesses, guardrails, and human-in-the-loop systems.
• Experience with frameworks such as LangChain, LlamaIndex, PyTorch, TensorFlow, or equivalent.
• Experience working with OpenAI, Azure OpenAI, Anthropic, Gemini, Hugging Face, or similar LLM platforms.
• Strong knowledge of REST APIs, microservices, databases, distributed systems, and cloud architectures.
• Experience with vector databases such as Pinecone, FAISS, Weaviate, Milvus, Chroma, or equivalent technologies.
• Hands-on experience with AWS/GCP/Azure AI and cloud services.
• Knowledge of Docker, Kubernetes, CI/CD, Git, and MLOps/LLMOps.
• Strong understanding of AI/LLM evaluation, benchmarking, monitoring, observability, optimization, and production deployment.
• Knowledge of AI/LLM security, including data protection, prompt injection, jailbreak risks, model risks, access controls, and secure tool execution.
• Understanding of AI system reliability, cost optimization, latency optimization, and scalable inference architectures.