AI/ML Engineer

Location: Mumbai

Role: Hybrid

Exp: 2-4 years

Role Overview

At Kennect, we are building a fully automated incentive management platform for some of India's largest enterprise companies, powering data-driven decision-making and sales incentive automation at scale. We are looking for proactive engineers with 2+ years of experience who want to build real AI and ML products, solve complex data problems, and take features from idea to production.

Key Responsibilities

• Build automated systems, RAG pipelines, AI agents, and multi-agent workflows using LangChain and LangGraph.
• Integrate AI agents into existing platform workflows and applications.
• Work deeply with LLMs, tool calling, context management, evaluation, inference, latency, and cost optimization.
• Design and optimize AI applications for production workloads, focusing on throughput, concurrency, reliability, and inference performance.
• Build ML models for classification, pattern recognition, forecasting, anomaly detection, and predictive insights on sales and incentive data.
• Work with enterprise datasets, embeddings, vector databases, retrieval pipelines, and data processing workflows.
• Identify bottlenecks and architectural gaps, research solutions, and independently drive improvements.
• Scale AI systems to support millions of users.
• Handle large-scale data for machine learning applications and agent workflows.
• Build deterministic and reliable agents.

Tech Stack

• Python - Machine Learning and experimentation
• Node.js / JavaScript - AI application backend and platform integration
• LangChain / LangGraph - LLM applications and agentic workflows
• Vector Databases - Embeddings, semantic search, and RAG
• LLMs & Inference - Model APIs (AWS Bedrock), inference, optimization, and scaling

Preferred Background

• 2+ years of engineering experience with strong Machine Learning fundamentals and/or hands-on AI implementation experience.
• Strong Python skills and hands-on experience building and deploying ML and AI models.
• Understanding of classification, pattern recognition, forecasting, and model evaluation.
• Ability to process and analyze large datasets.
• Hands-on experience with LLMs, RAG, embeddings, and vector databases.
• Strong understanding and experience with LangChain and LangGraph.
• Strong understanding of LLM fundamentals, inference, evaluation, cost estimation, and production scaling.
• Must have hands-on experience building and deploying applications using Node.js.

Qualifications

• Strong problem-solving and system design fundamentals.
• Must have hands-on experience building AI applications using Node.js and JavaScript.
• Strong ownership and ability to independently identify and solve problems.
• Comfortable working with ambiguity, messy data, and rapidly changing requirements.

What We Are Looking For

• Strong fit if you've deployed in-house LLM models or worked on an inference server.
• Engineers with 2+ YOE who have built real AI/ML or LLM applications.
• ML engineers who have deployed ML models and have experience handling large-scale data.
• AI engineers who have built more than just chatbots - including automated workflows.
• Software engineers with strong fundamentals and hands-on GenAI experience.

Good to Have

• Hands-on experience with llama.cpp and DuckDB.
• Hands-on experience with MongoDB / PostgreSQL.
• Knowledge of message queues like RabbitMQ.
• Knowledge of different LLM architectures (e.g., MoE).