Senior Technical Lead - Generative AI

Accountabilities

• • Architect, design, and develop Agentic AI and Generative AI solutions from early concepts and prototypes through production deployment.
  • Build multi-step reasoning agents, tool and function-calling workflows, memory systems, planning capabilities, and multi-agent architectures using frameworks such as LangGraph, AutoGen, CrewAI, or custom orchestration.
  • Design and productionize scalable Retrieval-Augmented Generation (RAG) pipelines covering chunking, embeddings, vector search, hybrid retrieval, and related retrieval strategies.
  • Evaluate and select foundation models based on accuracy, performance, latency, cost, and business requirements.
  • Develop and implement strategies for prompt engineering, model routing, fine-tuning, optimization, and continuous model improvement.
  • Own technical architecture decisions for reliable, scalable, secure, and cost-efficient LLM applications.
  • Establish engineering standards for AI testing, evaluation, observability, guardrails, hallucination mitigation, monitoring, and production reliability.
  • Design APIs, microservices, and cloud-native architectures that support AI applications at enterprise scale.
  • Drive AI/LLMOps practices covering model lifecycle management, deployment, monitoring, evaluation, and continuous improvement.
  • Lead, mentor, and develop AI/ML and backend engineering teams while maintaining strong technical standards.
  • Conduct architecture and technical design reviews, code reviews, and engineering discussions.
  • Remain hands-on with complex engineering challenges and provide technical direction across AI initiatives.
  • Partner with Product, Data Science, Platform, Security, and Compliance teams to align AI solutions with business objectives and organizational requirements.
  • Ensure AI systems address privacy, security, compliance, responsible-AI, and model-safety considerations.
  • Communicate complex AI and engineering concepts clearly to senior leadership and business stakeholders.
  • Represent the AI engineering function in strategic technology discussions, roadmap planning, and GenAI initiatives.

  Requirements

  • 10+ years of overall software engineering experience, including at least 4 years working directly with AI/ML systems.
  • 2+ years of hands-on experience building and deploying LLM-based or Agentic AI applications in production environments.
  • Deep expertise in LLM application development, RAG, embeddings, vector databases, prompt engineering, and AI-agent architectures.
  • Practical experience with multi-agent systems, tool/function calling, memory management, planning, and reasoning workflows.
  • Strong Python and software engineering fundamentals, with experience building scalable, distributed, production-grade systems.
  • Experience designing APIs, microservices, cloud-native architectures, and applications on at least one major cloud platform such as AWS, Azure, or GCP.
  • Hands-on experience with MLOps or LLMOps platforms such as MLflow, LangSmith, Weights & Biases, or equivalent technologies.
  • Working knowledge of LLM fine-tuning and evaluation techniques, including LoRA/PEFT, RLHF concepts, and offline/online evaluation frameworks.
  • Strong understanding of production AI engineering practices, including testing, observability, monitoring, guardrails, hallucination mitigation, and model evaluation.
  • Proven technical leadership experience, including architecture ownership, mentoring engineers, technical reviews, and cross-functional collaboration.
  • Excellent communication and stakeholder-management skills, with the ability to translate complex technical concepts into clear business and executive-level discussions.
  • Experience deploying or fine-tuning open-source models such as Llama or Mistral alongside proprietary models or APIs is advantageous.
  • Contributions to AI/GenAI open-source projects, technical publications, or conference presentations are a plus.
  • Experience developing AI solutions in regulated industries such as finance, healthcare, or telecommunications is desirable.
  • Knowledge of AI guardrails, red-teaming, responsible AI, model safety, and evaluation frameworks is beneficial.
  • Previous formal people-management experience is a plus.

  Benefits

  • Competitive annual compensation of approximately INR 30–50 LPA, depending on experience and skills.
  • Fully remote, full-time opportunity available across India.
  • Opportunity to lead the architecture and delivery of cutting-edge Generative AI and Agentic AI solutions.
  • Hands-on exposure to LLMs, multi-agent systems, RAG, LLMOps, cloud-native architectures, and emerging AI technologies.
  • Significant technical ownership and influence over AI engineering standards, architecture, and roadmap decisions.
  • Opportunity to mentor and develop AI/ML and backend engineering talent.
  • Cross-functional collaboration with Product, Data, Platform, Security, Compliance, and senior leadership teams.
  • Opportunity to solve complex enterprise problems and transition emerging AI capabilities into production-ready solutions.
  • Potential exposure to responsible AI, model safety, evaluation, and AI solutions in highly regulated environments.