Senior Technical Lead - Agentic AI / Generative AI

We are looking for a highly experienced Senior Technical Lead – Agentic AI / Generative AI to own the architecture, technical direction, and delivery of production-grade AI solutions. This is a hands-on leadership role for someone who can move seamlessly from early-stage experimentation and prototyping to scalable enterprise production systems.

You will design and build LLM-powered agentic systems, RAG architectures, multi-agent workflows, and AI applications, while mentoring a team of AI/ML and backend engineers. You will also work closely with Product, Data, Platform, Security, and other stakeholders to turn emerging GenAI capabilities into reliable, scalable, and business-ready solutions.

Key Responsibilities

AI Architecture & Development

• Architect and develop Agentic AI and Generative AI systems from concept through production.
• Build multi-step reasoning agents, tool/function-calling workflows, and multi-agent architectures using frameworks such as LangGraph, AutoGen, CrewAI, or custom orchestration.
• Design and productionize scalable RAG pipelines, including chunking, embeddings, vector search, and hybrid retrieval.
• Evaluate and select foundation models based on performance, accuracy, latency, cost, and business requirements.
• Develop strategies for prompt engineering, model routing, fine-tuning, and optimization.

Production Engineering

• Own technical architecture decisions for scalable, reliable, and cost-efficient LLM applications.
• Establish engineering standards covering testing, evaluation, observability, guardrails, hallucination mitigation, and production monitoring.
• Design APIs, microservices, and cloud-native architectures supporting AI applications at scale.
• Drive AI/LLMOps practices across model lifecycle management, deployment, monitoring, and continuous improvement.

Technical Leadership

• Lead, mentor, and develop AI/ML and backend engineers.
• Conduct technical design reviews, architecture discussions, and code reviews.
• Establish engineering best practices and promote high standards for production AI development.
• Provide technical direction while remaining actively involved in complex engineering problems.

Cross-Functional Collaboration

• Partner with Product, Data Science, Platform, Security, and Compliance teams to deliver AI solutions aligned with business objectives.
• Ensure AI systems meet appropriate privacy, security, compliance, and responsible-AI requirements.
• Communicate complex technical concepts clearly to senior leadership and business stakeholders.
• Represent the AI engineering function in strategic discussions around GenAI technology and roadmap decisions.

What's Makes You a Great Fit

• 10+ years of overall software engineering experience, including 4+ years working directly with AI/ML systems.
• At least 2+ years of hands-on experience building and deploying LLM-based or agentic AI applications in production.
• Deep expertise in LLM application development, RAG, embeddings, vector databases, prompt engineering, and AI agents.
• 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 with APIs, microservices, cloud-native architecture, and at least one major cloud platform such as AWS, Azure, or GCP.
• Hands-on experience with MLOps/LLMOps tools such as MLflow, LangSmith, Weights & Biases, or equivalent platforms.
• Working knowledge of LLM fine-tuning and evaluation techniques, including LoRA/PEFT, RLHF concepts, and offline/online evaluation frameworks.
• Proven ability to provide technical leadership, mentor engineers, own architecture decisions, and collaborate across teams.
• Strong communication skills with the ability to translate complex technical concepts into clear business and executive-level discussions.

Good to Have

• Experience deploying and fine-tuning open-source models such as Llama or Mistral, alongside proprietary models/APIs.
• Contributions to AI/GenAI open-source projects, technical publications, or conference presentations.
• Experience building AI solutions within regulated industries such as finance, healthcare, or telecom.
• Knowledge of AI guardrails, red-teaming, responsible AI, and model safety/evaluation frameworks.
• Previous formal people-management experience.