Senior AI Engineer

Spice Money; Dadri; On-site; INR 1,800,000 - 3,200,000; Full time

Job summary

Spice Money is seeking a Senior AI Engineer to lead the design, development, and deployment of AI-powered systems across our engineering platform. You will own the end-to-end lifecycle of AI features from research and prototyping through production reliability.

This high-ownership role requires building LLM-powered features, data pipelines, and AI governance to ship reliable, explainable AI that scales across teams and customers.

Qualifications

• 3-5 years of software engineering experience, with at least 2 years focused on AI/ML systems in production.
• Deep proficiency in Python; familiarity with TypeScript or Go is a plus.
• Hands-on experience with LLM frameworks LangChain, LangGraph, etc
• Experience building RAG systems, vector databases (Pinecone, Weaviate, pgvector), and semantic search pipelines.
• Strong understanding of model evaluation offline evals, human feedback loops, A/B testing, and hallucination detection.
• Proficiency with cloud AI services (AWS SageMaker, Azure ML, or GCP Vertex AI) and container-based deployments.
• Familiarity with data engineering and ETL pipelines that feed ML workflows.
• Excellent written and verbal communication able to explain model behaviour and trade-offs to non-technical stakeholders.

Responsibilities

• Design and implement LLM-powered features including agents, RAG pipelines, and evaluation frameworks integrated into production systems.
• Ownership.Own the full AI feature lifecycle: Prototype, evaluate, and deploy ML models and AI services including fine-tuning, prompt engineering, and model selection.
• Build and maintain robust data pipelines for model training, evaluation, and monitoring using tools such as Airflow, dbt, or Spark.
• Define and enforce AI quality standards including automated evals, red-teaming, and latency/accuracy benchmarking.
• Collaborate with product, design, and infrastructure teams to ship AI features that are reliable, explainable, and scalable.
• Establish best practices for AI tooling, code review for ML code, and engineering standards across the AI function.
• Mentor engineers on applied AI techniques, model evaluation, and responsible AI usage.
• Contribute to vendor assessment including evaluation of AI tools such as Cursor, Claude, GitHub Copilot, and internal LLM deployments.

Skills

Python

LLM frameworks

LangChain

LangGraph

RAG systems

Vector databases

Semantic search

Cloud AI services

Docker/Kubernetes

ETL pipelines

Communication

Tools

LangChain

LangGraph

Pinecone

Weaviate

pgvector

Airflow

dbt

Spark

Kubernetes

Terraform

Job description

ABOUT THE ROLE:

We are hiring a Senior AI Engineer to lead the design, development, and deployment of AI-powered systems across our engineering platform. You will work at the intersection of applied machine learning, software engineering, and product delivery building systems that directly impact how our teams ship software and serve customers.

This is a high-ownership role. You will not just integrate AI APIs you will own the end-to-end lifecycle of AI features, from research and prototyping through production reliability.

KEY RESPONSIBILITIES:

• Design and implement LLM-powered features including agents, RAG pipelines, and evaluation frameworks integrated into production systems.
• Ownership.Own the full AI feature lifecycle:
• Prototype, evaluate, and deploy ML models and AI services including fine-tuning, prompt engineering, and model selection.
• Build and maintain robust data pipelines for model training, evaluation, and monitoring using tools such as Airflow, dbt, or Spark.
• Define and enforce AI quality standards including automated evals, red-teaming, and latency/accuracy benchmarking.
• Collaborate with product, design, and infrastructure teams to ship AI features that are reliable, explainable, and scalable.
• Establish best practices for AI tooling, code review for ML code, and engineering standards across the AI function.
• Mentor engineers on applied AI techniques, model evaluation, and responsible AI usage.
• Contribute to vendor assessment including evaluation of AI tools such as Cursor, Claude, GitHub Copilot, and internal LLM deployments.

REQUIRED QUALIFICATIONS:

• 3-5 years of software engineering experience, with at least 2 years focused on AI/ML systems in production.
• Deep proficiency in Python; familiarity with TypeScript or Go is a plus.
• Hands-on experience with LLM frameworks LangChain, LangGraph, etc
• Experience building RAG systems, vector databases (Pinecone, Weaviate, pgvector), and semantic search pipelines.
• Strong understanding of model evaluation offline evals, human feedback loops, A/B testing, and hallucination detection.
• Proficiency with cloud AI services (AWS SageMaker, Azure ML, or GCP Vertex AI) and container-based deployments.
• Familiarity with data engineering and ETL pipelines that feed ML workflows.
• Excellent written and verbal communication able to explain model behaviour and trade-offs to non-technical stakeholders.

PREFERRED QUALIFICATIONS:

• Experience with fine-tuning or RLHF on open-source models (LLaMA, Mistral, Falcon, or similar).
• Background in NLP, information retrieval, or recommendation systems.
• Familiarity with AI governance, data privacy compliance, and responsible AI frameworks.
• Experience evaluating or deploying AI copilot tooling (Cursor, GitHub Copilot, Codeium) at team or org level.

OUR AI & ENGINEERING STACK

Languages Python (primary), TypeScript, SQL

LLM / AI Anthropic Claude, OpenAI GPT-4o, LangChain, LlamaIndex

Vector DBs pgvector, Pinecone, Weaviate

Infra AWS, Docker, Kubernetes, Terraform

Data dbt, Airflow, Snowflake, Spark

Dev tools Cursor (enterprise), GitHub Copilot, Claude.ai Team