Intermediate Analyst, Risk Modeling Solutions – Full-stack GenAI

Jobtailor; Bengaluru; On-site; INR 1,200,000 - 1,800,000; Full time

Job summary

Jobtailor in Bengaluru, India seeks an experienced AI systems engineer blending software development and data science. You will build scalable Python microservices, design robust AI workflows, and own deployment pipelines using containerization and modern orchestration.

Applicants should have 4+ years in AI/ML with hands-on experience in LangChain or related orchestration tools, RAG architectures, and cloud AI platforms. Prior work in regulated domains is a plus.

Qualifications

• 4+ years of software development and ML experience.
• Strong Python for AI systems and backend services.
• Production APIs with FastAPI and microservices architecture.
• Proficiency with Docker and Kubernetes for deployments.
• Hands-on with agentic AI or LLM orchestration frameworks.
• Practical RAG experience with vector databases.
• Cloud AI platform experience (AWS Bedrock, Azure, or GCP).
• Familiarity with Git workflows and collaborative development.
• Knowledge of NLP fundamentals and Transformer architectures.
• Experience in regulated enterprise environments is a plus.

Responsibilities

• Implement end-to-end agentic AI workflows using LangGraph, CrewAI, and AutoGen.
• Build and optimize retrieval pipelines, memory layers, and tool-use sequences with LangChain.
• Develop robust Python-based microservices and REST APIs using FastAPI.
• Construct and refine RAG pipelines with embedding and vector search (Azure/OpenSearch/Pinecone).
• Package AI services with Docker and deploy on Kubernetes; contribute to CI/CD.
• Instrument AI workflows using Langfuse for tracing and debugging.
• Implement evaluation harnesses to ensure model quality and performance.
• Participate in code reviews and maintain technical documentation.

Skills

Python

NLP

Transformer models

Git workflows

Backend services

API design

ML engineering

Team collaboration

Tools

FastAPI

Docker

Kubernetes

LangChain

LangGraph

CrewAI

LlamaIndex

OpenSearch

Pinecone

Chroma

Snowflake

Redshift

AWS Bedrock

Azure AI Foundry

GCP Vertex AI

Job description

Responsibilities

• Implement end-to-end agentic AI workflows using frameworks like LangGraph, CrewAI, and AutoGen, focusing on reasoning, tool use, and memory.
• Build and optimize retrieval pipelines, memory layers, and tool-use sequences using frameworks like LangChain.
• Develop robust, scalable Python-based microservices and REST APIs using FastAPI to expose AI capabilities.
• Construct and refine Retrieval-Augmented Generation (RAG) pipelines, including document ingestion, embedding, and vector search integration with databases like Azure AI Search or Pinecone.
• Package AI services using Docker and deploy them on Kubernetes, contributing to CI/CD pipelines for smooth and reliable releases.
• Instrument AI workflows using platforms like Langfuse for tracing and debugging.
• Implement and maintain evaluation harnesses to ensure model quality and performance.
• Actively participate in code reviews, contribute to technical documentation, and collaborate with team members to uphold high engineering standards.

Requirements

• 4+ years of professional experience in a role blending software development and data science/machine learning.
• Strong Python development expertise for AI systems and backend services.
• Experience building production APIs with FastAPI and microservices architecture.
• Proficiency with Docker and Kubernetes for containerized deployments.
• Hands‑on experience with agentic AI or LLM orchestration frameworks (e.g., LangChain, LangGraph, CrewAI, LlamaIndex).
• Practical experience with RAG architecture, including vector databases (e.g., OpenSearch, Pinecone, Chroma).
• Proven ability to design and implement cost‑effective AI architectures, with a deep understanding of tokenomics, model‑tiering strategies, and caching for performance and budget management.
• Familiarity with Git‑based workflows and collaborative development practices.
• A solid understanding of NLP fundamentals and Transformer architectures.
• Preferred Qualifications: Experience with Langfuse or similar AI observability platforms.
• Hands‑on use of a major cloud AI platform (AWS Bedrock, Azure AI Foundry, or GCP Vertex AI).
• Familiarity with enterprise data platforms like Snowflake or Redshift.
• Background in financial services or another regulated enterprise environment.

Core Competencies

Demonstrates expertise in developing and optimizing AI workflows, microservices, and APIs, with a strong focus on Python, containerization, and retrieval‑augmented generation techniques. Proficient in implementing scalable AI architectures and collaborating in high‑standard engineering environments.