Technical Lead GenAI / LLM Solutions

Tekskills Inc.; Delhi; On-site; INR 3,500,000 - 6,500,000; Full time

Job summary

Tekskills Inc. in Delhi is seeking a hands-on Technical Lead with deep GenAI expertise to lead delivery of a client-facing GenAI platform.

You will drive architecture, design, and implementation of LLM-based systems, while coordinating with clients to translate business problems into scalable AI capabilities. The role requires strong technical leadership, active coding, and mentoring of engineers to maintain high delivery standards and responsible AI practices across cloud environments and MLOps

Qualifications

• 10-15 years of software engineering experience.
• 4+ years in a Tech Lead role.
• Proven hands-on delivery of GenAI/LLM solutions in production.
• Experience working with clients or external stakeholders.
• Strong experience with LLM platforms (Azure OpenAI, OpenAI, Anthropic, or open-source models).
• Deep understanding of RAG architectures, embeddings, and vector databases.
• Experience with GenAI frameworks (LangChain, LlamaIndex, Semantic Kernel, etc.).
• Strong programming skills in Python (preferred) and/or JavaScript/TypeScript.
• Experience with cloud platforms (AWS, Azure, or GCP), APIs, and microservices.
• CI/CD and DevOps/MLOps exposure.

Responsibilities

• Own end-to-end technical delivery of GenAI solutions for the Genie Project.
• Act as the primary technical point of contact for clients.
• Be actively hands-on with design, development, review, and optimization of GenAI and backend code.
• Architect and implement LLM-based systems (RAG, agents, prompt workflows).
• Translate client requirements into scalable, secure technical solutions.
• Guide best practices for prompt engineering, model usage, evaluation, and observability.
• Mentor engineers and ensure high engineering and delivery standards.
• Ensure performance, cost efficiency, security, and responsible AI compliance.
• Support client demos, technical discussions, and solution walkthroughs.

Skills

GenAI expertise

LLM system design

Client communication

Hands-on coding

Python

Cloud platforms

Tools

LangChain

LlamaIndex

Semantic Kernel

Azure OpenAI

OpenAI

Job description

Job Summary

We are looking for a hands-on Technical Lead with deep GenAI expertise to lead delivery of a client-facing GenAI platform. This role requires strong technical leadership, active coding, and the ability to work closely with clients to define, design, and deliver scalable GenAI solutions. The ideal candidate combines LLM system design, engineering excellence, and client communication skills to translate business problems into production-ready AI capabilities.

Responsibilities

• Own end-to-end technical delivery of GenAI solutions for the Genie Project
• Act as the primary technical point of contact for clients
• Be actively hands-on with design, development, review, and optimization of GenAI and backend code
• Architect and implement LLM-based systems (RAG, agents, prompt workflows)
• Translate client requirements into scalable, secure technical solutions
• Guide best practices for prompt engineering, model usage, evaluation, and observability
• Mentor engineers and ensure high engineering and delivery standards
• Ensure performance, cost efficiency, security, and responsible AI compliance
• Support client demos, technical discussions, and solution walkthroughs

Required Skills & Experience

• 10-15 years of software engineering experience; 4+ years in a Tech Lead role
• Proven hands-on experience delivering GenAI / LLM solutions in production
• Experience working directly with clients or external stakeholders
• Strong experience with LLM platforms (Azure OpenAI, OpenAI, Anthropic, or open-source models)
• Deep understanding of RAG architectures, embeddings, and vector databases
• Experience with GenAI frameworks (LangChain, LlamaIndex, Semantic Kernel, etc.)
• Strong programming skills in Python (preferred) and/or JavaScript/TypeScript
• Experience with cloud platforms (AWS, Azure, or GCP), APIs, and microservices
• CI/CD and DevOps/MLOps exposure