Senior Software Engineer - Data License Analytics, Pune

Bloomberg; Maharashtra; On-site; INR 1,800,000 - 2,400,000; Full time

Job summary

Bloomberg Pune-based team seeks a senior engineer to advance the Data License Analytics Platform. You will join an intersection of data infrastructure, reliability engineering, and applied AI to make Bloomberg’s data delivery more reliable and scalable.

Responsibilities include building GenAI tooling for incident triage, ingestion pipelines into Iceberg, semantic search with embeddings, and self-service APIs for partner onboarding.

Qualifications

• 6+ Software engineering experience in production environments.
• Proficiency in Python or a similar language.
• Familiarity with relational databases and SQL.
• Interest or experience in data engineering — pipelines, batch processing, or data lake technologies.
• Understanding of distributed systems and service architecture.
• Interest in AI/ML — particularly LLMs, RAG, or embedding-based search.

Responsibilities

• Build GenAI tools and AI agents — RAG pipelines, contextual embedding systems, and MCP tool servers that give LLM agents structured access to live pipeline data.
• Build and maintain data ingestion pipelines into Apache Iceberg, orchestrated via Apache Airflow.
• Develop semantic search capabilities using vector databases and hosted embedding models.
• Build self-service ingestion APIs enabling partner teams to onboard to the platform without managing Iceberg or storage infrastructure.
• Design microservices and backend APIs — with opportunities to contribute to React/TypeScript interfaces embedded in production tools.
• Instrument systems with OpenTelemetry and contribute to anomaly detection capabilities on the near-term roadmap.

Skills

Python

SQL

Distributed Systems

AI/ML

Tools

Apache Iceberg

Apache Airflow

PyArrow

PyIceberg

Spark

Kafka

RabbitMQ

Parquet

PostgreSQL

Vector databases

Redis

Solr

Docker

Kubernetes

NGINX

OpenTelemetry

GCP

AWS

Snowflake

Databricks

RAG frameworks

Embedding models

LLM integration

MCP

A2A

Job description

Location

Pune

Business Area

Engineering and CTO

Ref #

10053865

Description & Requirements

About the Team

Data License is Bloomberg's enterprise data delivery platform, powering financial institutions worldwide with reference, pricing, regulatory, and alternative data — covering over 50 million securities across portfolio accounting, risk, compliance, and trading use cases.

The DL Analytics Platform is the intelligence and reliability layer of this ecosystem. We build the data ingestion pipelines, embeddings infrastructure, AI agents, and MCP tool servers that give engineers and LLMs structured, query able access to operational data. Our systems power incident triage, semantic search over tickets and documentation, pipeline health analytics, and self-service data onboarding for partner teams across Data License.

We are expanding our engineering presence into Pune and the broader APAC region — a greenfield initiative where engineers will collaborate closely with colleagues in Dublin, London, and New York, helping shape the culture and technical direction of this hub from day one.

What's the role?

You’ll join a team at the intersection of data infrastructure, reliability engineering, and applied AI — building systems that make Bloomberg’s data delivery more reliable, intelligent, and scalable.

Reliability Engineering: GenAI-powered tooling for incident triage, root-cause analysis, and blast radius assessment — exposing live pipeline data to LLM agents via MCP tool servers.

Data Analytics & AI: Ingestion pipelines into Apache Iceberg, semantic search over operational data using vector databases and embedding models, and automated KPI tracking to surface platform health and anomalies.

We'll Trust You To

• Build GenAI tools and AI agents — RAG pipelines, contextual embedding systems, and MCP tool servers that give LLM agents structured access to live pipeline data
• Build and maintain data ingestion pipelines into Apache Iceberg, orchestrated via Apache Airflow
• Develop semantic search capabilities using vector databases and hosted embedding models
• Build self-service ingestion APIs enabling partner teams to onboard to the platform without managing Iceberg or storage infrastructure
• Design microservices and backend APIs — with opportunities to contribute to React/TypeScript interfaces embedded in production tools
• Instrument systems with OpenTelemetry and contribute to anomaly detection capabilities on the near-term roadmap

Technologies

• Languages & Frameworks: Python (3.11 / 3.12 / 3.13), TypeScript, FastAPI, React
• Data & Orchestration: Apache Iceberg, Apache Airflow, PyArrow, PyIceberg, Spark, Kafka, RabbitMQ, Parquet
• Databases: PostgreSQL, vector databases, Redis, Solr, distributed SQL
• Infrastructure: Docker, Kubernetes, NGINX, OpenTelemetry
• Cloud: GCP, AWS (S3, Redshift), Snowflake, Databricks
• AI & ML: RAG frameworks, embedding models, contextual chunking, semantic search, LLM integration
• Agent Frameworks: MCP (Model Context Protocol), Agent-to-Agent (A2A)

You’ll Need To Have

• 6+ Software engineering experience in production environments
• Proficiency in Python or a similar language
• Familiarity with relational databases and SQL
• Interest or experience in data engineering — pipelines, batch processing, or data lake technologies
• Understanding of distributed systems and service architecture
• Interest in AI/ML — particularly LLMs, RAG, or embedding-based search

We’d Love To See

• Experience with Apache Iceberg, PyArrow, or data lake engineering
• Familiarity with Apache Airflow or workflow orchestration
• Experience with vector databases, embedding models, or semantic searchBackground in anomaly detection or data quality frameworks
• Exposure to MCP, A2A, or agent communication protocols
• Experience with observability tooling — tracing, metrics, structured logging
• Curiosity about financial data and reliability engineering

Why Join Us

• Ship GenAI tooling used daily in production — MCP servers, RAG pipelines, and AI agents for real incident triage
• Be a founding member of a greenfield engineering hub — shape the culture and standards from day one
• Collaborate with engineers across Dublin, London, and New York
• Work at scale — millions of securities, billions of data points, clients depending on it around the clock
• Join a team that values curiosity, learning, and measurable impact

Discover what makes Bloomberg unique - watch our for an inside look at our culture, values, and the people behind our success.