Lead AI Engineer

DoubleTick; Mumbai; On-site; INR 4,000,000 - 7,000,000; Full time

Job summary

DoubleTick, based in Mumbai, seeks an AI Lead Engineer to architect and ship production-grade AI systems, including LLMs, RAG pipelines, and speech AI. You will own the AI stack from model selection to deployment, building scalable features for a conversational CRM platform and guiding engineering best practices.

You will work hands-on, writing code, evaluating models, and mentoring engineers, while partnering with product and leadership to scale AI capabilities across the product.

Qualifications

• 5+ years of software engineering experience with hands-on AI/ML in production.
• Strong understanding of Generative AI and LLM-based development.
• Hands-on with OpenAI, Anthropic, Gemini, Llama, Mistral or similar models.
• Experience with fine-tuning LLMs and speech models for domain needs.
• Experience deploying AI in production and dealing with latency, cost, and observability.

Responsibilities

• Design and build LLM-powered applications and AI features for DoubleTick's conversational CRM platform.
• Architect and develop AI agents, intelligent workflows, chatbots, copilots, and automation systems.
• Build production-grade RAG pipelines using embeddings, vector databases, retrieval, reranking, and contextual generation.
• Work with LLM APIs and open-source models to select models and architectures.
• Fine-tune and adapt LLMs and speech models for domain-specific accuracy and performance.
• Build and optimize speech AI systems, including speech-to-text, text-to-speech, and voice-based pipelines.
• Develop robust prompt engineering and evaluation frameworks to improve accuracy and cost.
• Build observability, monitoring, evaluation, guardrails and failure handling for AI systems.
• Self-host, deploy, and scale AI infrastructure across GPU environments.
• Integrate AI capabilities with backend services, APIs, databases, and product workflows.
• Ensure performance, scalability, reliability and cost-efficiency of AI systems.

Skills

AI/ML development

LLM-based apps

System design

Python

NLP

LangChain

Kubernetes

Docker

Prompt engineering

GPU infrastructure

Tools

PyTorch

TensorFlow

LangChain

Weaviate

Qdrant

Milvus

pgvector

Job description

As an AI Lead Engineer, you will be responsible for designing, building, and scaling production-grade AI systems that solve real customer and business problems.

You will work closely with Product, Engineering, and leadership teams to identify AI opportunities and turn them into reliable, scalable features. The role is highly hands-on—you will be expected to architect solutions, write code, experiment with models, evaluate AI performance, and take AI features from prototype to production.

You will have significant ownership over the AI engineering stack, including LLMs, RAG, AI agents, prompt engineering, model fine-tuning, speech/voice AI, model evaluation, AI workflows, and production infrastructure.

Key Responsibilities

• Design and build LLM-powered applications and AI features for DoubleTick's conversational CRM platform.
• Architect and develop AI agents, intelligent workflows, chatbots, copilots, and automation systems.
• Build production-grade RAG pipelines using embeddings, vector databases, retrieval, reranking, and contextual generation.
• Work with LLM APIs and open-source models to identify the right model and architecture for different use cases.
• Fine-tune and adapt LLMs and speech models for domain-specific accuracy, tone, and performance.
• Build and optimize speech AI systems, including speech-to-text, text-to-speech, and voice‑based conversational pipelines.
• Develop robust prompt engineering and evaluation frameworks to improve accuracy, relevance, latency, and cost.
• Build systems for LLM observability, monitoring, evaluation, guardrails, and failure handling.
• Self-host, deploy, and scale AI infrastructure (LLMs, speech models, vector databases) across GPU environments.
• Integrate AI capabilities with existing backend services, APIs, databases, and product workflows.
• Optimize AI systems for performance, scalability, reliability, and cost.
• Experiment with new AI/ML technologies and rapidly convert successful experiments into production solutions.
• Work closely with Product and Engineering teams to define AI use cases and technical approaches.
• Establish engineering best practices around AI development, testing, deployment, and monitoring.
• Mentor engineers and provide technical leadership on AI-related initiatives.

What We're Looking For

• 5+ years of software engineering experience, with significant hands‑on experience building AI/ML‑powered applications.
• Strong understanding of Generative AI and LLM-based application development.
• Hands‑on experience with LLMs such as OpenAI, Anthropic, Gemini, Llama, Mistral, or similar models.
• Hands‑on experience fine‑tuning LLMs (LoRA/QLoRA, full fine‑tuning, RLHF/DPO, or similar techniques).
• Experience working with speech models—ASR/STT, TTS, or voice AI pipelines.
• Experience fine‑tuning speech models (e.g., Whisper or similar ASR/TTS architectures) for domain‑specific use cases.
• Experience self‑hosting and scaling AI infrastructure in production (GPU provisioning, model serving, load balancing, autoscaling).
• Strong experience building RAG‑based systems and working with embeddings/vector search.
• Experience with AI agents, tool calling, function calling, workflow orchestration, or similar architectures.
• Strong understanding of prompt engineering, context management, structured outputs, and LLM evaluation.
• Experience working with vector databases such as Pinecone, Weaviate, Qdrant, Milvus, pgvector, or equivalent.
• Strong understanding of APIs, microservices, databases, distributed systems, and backend architecture.
• Experience deploying AI applications in production environments.
• Good understanding of AI system challenges including hallucination, latency, token/cost optimization, reliability, security, and observability.
• Strong problem‑solving and system‑design skills.

Good to Have

• Experience building conversational AI / chatbots / voice AI.
• Experience with WhatsApp, messaging, CRM, customer support, sales automation, or Martech products.
• Experience with fine‑tuning or adapting open‑source LLMs and speech models.
• Experience with LangChain, LangGraph, LlamaIndex, Semantic Kernel, or similar frameworks.
• Experience with ML frameworks such as PyTorch or TensorFlow.
• Experience with AWS, GCP, Azure, or other cloud platforms.
• Experience with Kubernetes, Docker, CI/CD, and production AI infrastructure.
• Experience self‑hosting open‑source models (LLMs or speech models) at scale.
• Experience building AI evaluation and experimentation platforms.
• Experience working in a SaaS / product company is highly preferred.

What You'll Own

• AI architecture and technical direction
• LLM and AI‑agent infrastructure
• Model fine‑tuning and speech AI systems
• RAG and knowledge systems
• AI experimentation and evaluation
• Self‑hosted, scaled AI infrastructure
• Production AI reliability and observability
• AI performance and cost optimization
• Integration of AI into DoubleTick's core product

About DoubleTick

DoubleTick.io headquartered in Mumbai, is a Meta award‑winning AI conversational CX stack, designed to unlock conversation‑led sales, marketing, and customer engagement use‑cases at scale for enterprises. Backed by Info Edge Ventures and BeeNext, the platform serves 10,000+ businesses across India and UAE and serves large clients across various industries like BFSI, Real Estate, Travel, EdTech, Healthcare, Auto, Retail and FMCG. Leading brands such as MakeMyTrip, Piramal Finance, CoinDCX, AU Bank, Lodha Developers among many others trust DoubleTick to power their customer conversations.

The UX friendly enterprise communication suite features a full‑stack conversational platform featuring conversational centralization, automation and analytics across channels like WhatsApp chat, WhatsApp Voice, WhatsApp Groups, PSTN Calls among 10+ other channels. With its AI Agent Builder and Bot Studio enterprises can create and deploy complex AI Agents and Bots across chat and voice in minutes.

Why work with us?

• Fast‑tracked career success into senior leadership positions
• Opportunity to own high value work and create impact at scale
• Opportunity to work closely with the founders and learn what it takes to grow a company in each stage of growth.
• Opportunity to work in a cultural environment where you can challenge founders/leadership and reason with them on any issue.
• Direct exposure to working with some of the largest enterprises in the world.